© 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. 43493
    Prev
    Next
    INDEX
    Explanations

    scientific research/drugs

    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
    æ¯ĶåĪ©
    -0.31
    erto
    -0.27
    .dispatch
    -0.26
    vector
    -0.25
    dispatch
    -0.25
    è·Įçł´
    -0.25
     purposely
    -0.25
    vro
    -0.24
    æ²īæ·Ģ
    -0.24
    çŁ¥
    -0.24
    POSITIVE LOGITS
    Ỽ
    0.29
    owe
    0.26
    neau
    0.26
    esz
    0.25
    theses
    0.25
    eca
    0.24
    æ¶Ľ
    0.24
    æªĶ
    0.24
     RAT
    0.24
    è´ŀ
    0.24
    Activations Density 0.005%

    No Known Activations