Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 71584
    Prev
    Next
    INDEX
    Explanations

    foreign words or code

    np_max-act-logits · gemini-2.0-flash

    prescriptive medical or health advice and instructions on what someone should do or take.

    oai_token-act-pair · claude-4-5-haikuTriggered by @xiaoqingsun004
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كرة
    -0.07
    俳
    -0.07
    .arg
    -0.07
     Caroline
    -0.07
    乩
    -0.07
     işçi
    -0.07
    犰
    -0.07
    ��
    -0.06
    afone
    -0.06
    imum
    -0.06
    POSITIVE LOGITS
    不含
    0.08
    _RATE
    0.08
    /logger
    0.07
    _fail
    0.07
    有关部门
    0.07
    阿姨
    0.07
    .configuration
    0.07
    _stub
    0.07
     проблемы
    0.07
    ureen
    0.07
    Activations Density 0.007%

    No Known Activations