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. 70539
    Prev
    Next
    INDEX
    Explanations

    tree data structures

    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
     btnSave
    -0.08
    opath
    -0.07
     منتخب
    -0.07
     HinderedRotor
    -0.07
    inidad
    -0.07
     Nicholson
    -0.07
    Ⴝ
    -0.07
     doi
    -0.06
    太阳能
    -0.06
     ethnic
    -0.06
    POSITIVE LOGITS
    른
    0.07
    דק
    0.07
    背后的
    0.07
    acct
    0.07
    最早的
    0.07
    *a
    0.07
    wc
    0.07
    Encoder
    0.07
    就会
    0.07
    슐
    0.06
    Activations Density 0.009%

    No Known Activations