© 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. 35-TRANSCODER-HP
    7. 39740
    Prev
    Next
    INDEX
    Explanations

    miscellaneous text snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resident
    -0.26
    teen
    -0.25
    è¿ĻéĩĮéĿ¢
    -0.25
    èŀ³
    -0.25
    ĵ
    -0.25
    OVE
    -0.25
     differently
    -0.25
    ecc
    -0.24
     undes
    -0.24
     Äijâu
    -0.24
    POSITIVE LOGITS
    porno
    0.31
    storm
    0.31
    std
    0.30
    lude
    0.30
    stop
    0.29
    stial
    0.28
    cloak
    0.28
    bower
    0.28
    utherland
    0.27
    brew
    0.27
    Activations Density 0.066%

    No Known Activations