© 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. 41875
    Prev
    Next
    INDEX
    Explanations

    Research context

    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
     Curtain
    -0.30
     Cups
    -0.29
    ié
    -0.28
    tron
    -0.27
    ·¨
    -0.26
    纵
    -0.26
    è£ĺ
    -0.25
    ragon
    -0.25
    æįŁä¼¤
    -0.25
    æ©«
    -0.25
    POSITIVE LOGITS
    CEED
    0.27
    getObject
    0.25
    åIJĪæ³ķ
    0.25
    .Override
    0.24
    º«
    0.24
    颢
    0.24
    å¯Į
    0.23
    lege
    0.23
    _SEQUENCE
    0.23
    igers
    0.23
    Activations Density 0.000%

    No Known Activations