© 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. 32-TRANSCODER-HP
    7. 43173
    Prev
    Next
    INDEX
    Explanations

    immune

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sol
    -0.29
    оÑĢÑĤ
    -0.26
    çĻ¾å¹´
    -0.25
    ekt
    -0.25
    .RequestMethod
    -0.25
     wheels
    -0.24
     PhÆ°Æ¡ng
    -0.24
    ury
    -0.24
    undy
    -0.24
    .sol
    -0.24
    POSITIVE LOGITS
     function
    0.34
     axis
    0.29
    æľ«
    0.29
    -related
    0.28
     response
    0.28
    function
    0.27
     reaction
    0.27
    arin
    0.27
    lef
    0.27
    å¯ĨåĪĩ缸åħ³
    0.27
    Activations Density 0.008%

    No Known Activations