© 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. 57454
    Prev
    Next
    INDEX
    Explanations

    religious texts

    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
    转åıij
    -0.26
    омеÑĢ
    -0.26
    adb
    -0.26
    afb
    -0.25
    gmt
    -0.25
    ErrorException
    -0.24
    éĢĢåĽŀ
    -0.24
    åĽ½éĻħåľ¨çº¿
    -0.24
    åĪĨæľŁ
    -0.24
    èłĸ
    -0.24
    POSITIVE LOGITS
     his
    0.32
     himself
    0.31
     hall
    0.28
    lena
    0.26
    enas
    0.26
    nap
    0.26
     us
    0.25
     public
    0.25
     Plans
    0.25
    ä»ĸçļĦ
    0.25
    Activations Density 0.008%

    No Known Activations