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. 130896
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    㶳
    -0.07
    asn
    -0.07
    墁
    -0.07
     intox
    -0.07
    _^(
    -0.07
    的信息
    -0.07
     asleep
    -0.06
    ᭣
    -0.06
    תכנ
    -0.06
    ﮇ
    -0.06
    POSITIVE LOGITS
    本地
    0.07
     callback
    0.07
     selection
    0.07
    퍠
    0.07
     nacional
    0.07
    摆脱
    0.06
    做出了
    0.06
    回调
    0.06
    checkout
    0.06
    .ci
    0.06
    Activations Density 0.139%

    No Known Activations