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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 8064
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pil
    -0.32
    çĪ¶æ¯į
    -0.31
     witnessing
    -0.27
    _parents
    -0.27
    æķ°åŃĹ
    -0.27
    çijĹ
    -0.27
    );$
    -0.27
     parent
    -0.26
    åŁİåİ¿
    -0.26
    parent
    -0.26
    POSITIVE LOGITS
    æıIJåĩº
    0.27
     fame
    0.25
    说çļĦæĺ¯
    0.25
     çı
    0.25
    ç¼ĸåĨĻ
    0.25
    满æĢĢ
    0.25
    çĶ¨å¿ĥ
    0.24
    ARATION
    0.24
    RFC
    0.24
     Staples
    0.23
    Activations Density 0.004%

    No Known Activations