© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 2980
    Prev
    Next
    INDEX
    Explanations

    Technical forum posts

    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
     hus
    -0.07
    	pid
    -0.07
    퓶
    -0.06
    ANCELED
    -0.06
     swój
    -0.06
    iah
    -0.06
    POR
    -0.06
    maybe
    -0.06
     �
    -0.06
    _heat
    -0.06
    POSITIVE LOGITS
    unta
    0.07
     ListView
    0.07
    实习
    0.07
    оль
    0.07
    桌面
    0.07
    verbatim
    0.07
     playlists
    0.07
    /accounts
    0.07
    שיבה
    0.07
    models
    0.06
    Activations Density 0.002%

    No Known Activations