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. 6997
    Prev
    Next
    INDEX
    Explanations

    programming/computer code

    np_max-act-logits · gemini-2.0-flash

    factually incorrect or overconfident assertions presented with certainty.

    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
    مسأل
    -0.09
    Iterator
    -0.08
     chemotherapy
    -0.07
    .setMessage
    -0.07
    declspec
    -0.06
    useppe
    -0.06
    邬
    -0.06
    WithTag
    -0.06
     отказ
    -0.06
     fakt
    -0.06
    POSITIVE LOGITS
    حت
    0.08
    ḩ
    0.07
    돔
    0.07
    Ᵽ
    0.07
    𝙠
    0.07
    ğu
    0.07
    ptype
    0.07
    .Ok
    0.07
    ublished
    0.07
    undo
    0.07
    Activations Density 0.125%

    No Known Activations