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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 31456
    Prev
    Next
    INDEX
    Explanations

    nullptr

    np_max-act-logits · gemini-2.0-flash
    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
     regimen
    -0.07
     Boxing
    -0.07
     airy
    -0.07
    机电
    -0.07
    .Sub
    -0.07
    倏
    -0.07
    馗
    -0.07
     alert
    -0.07
    消费品
    -0.07
     المسلحة
    -0.07
    POSITIVE LOGITS
    postcode
    0.07
    𝑟
    0.07
     £
    0.07
    库
    0.07
    (encoded
    0.07
    enden
    0.07
    ɴ
    0.07
    stairs
    0.06
    _answer
    0.06
    。</
    0.06
    Activations Density 0.001%

    No Known Activations