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. 71836
    Prev
    Next
    INDEX
    Explanations

    CU

    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
    rov
    -0.07
    Ant
    -0.07
    Report
    -0.07
    _cls
    -0.07
    琥
    -0.07
    _items
    -0.06
    keeping
    -0.06
    _entity
    -0.06
    的生命
    -0.06
     boolean
    -0.06
    POSITIVE LOGITS
    (cx
    0.08
    バレ
    0.07
     WCS
    0.07
    הד
    0.07
    ASCADE
    0.07
    נצ
    0.07
     [|
    0.07
     Malta
    0.07
     בש
    0.07
     שינוי
    0.07
    Activations Density 0.001%

    No Known Activations