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. 59856
    Prev
    Next
    INDEX
    Explanations

    required

    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
    לוט
    -0.07
    Sure
    -0.07
    _decision
    -0.07
    drawable
    -0.07
    pData
    -0.07
    大家可以
    -0.07
    Folders
    -0.07
    live
    -0.07
    fast
    -0.07
    ataire
    -0.07
    POSITIVE LOGITS
     прием
    0.07
     nib
    0.07
    聿
    0.07
     PyQt
    0.06
    yện
    0.06
     eius
    0.06
    еньк
    0.06
    Projects
    0.06
    弘扬
    0.06
    yectos
    0.06
    Activations Density 0.004%

    No Known Activations