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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7299
    Prev
    Next
    INDEX
    Explanations

    ?

    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
     SMS
    -0.07
     tử
    -0.07
     Damien
    -0.07
     Smoke
    -0.07
     sue
    -0.07
    (Q
    -0.07
    僎
    -0.07
    erals
    -0.07
    Serialization
    -0.07
     FX
    -0.07
    POSITIVE LOGITS
    .edit
    0.07
     intensified
    0.07
     upgraded
    0.07
    .smtp
    0.06
    ENU
    0.06
    wik
    0.06
    rar
    0.06
     results
    0.06
    faith
    0.06
    盉
    0.06
    Activations Density 0.005%

    No Known Activations