© 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. 31-TRANSCODER-HP
    7. 18821
    Prev
    Next
    INDEX
    Explanations

    After

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -0.37
     its
    -0.29
    its
    -0.27
    为åħ¶
    -0.26
     coloured
    -0.25
    ç§ijæĬĢèĤ¡ä»½
    -0.25
    ä¸İåħ¶
    -0.25
     illustration
    -0.25
     Its
    -0.25
    ãģĻãģĶ
    -0.24
    POSITIVE LOGITS
     moving
    0.41
    Moving
    0.36
    moving
    0.35
     leaving
    0.33
     Moving
    0.33
     moves
    0.32
     quickly
    0.30
     gaining
    0.30
    leave
    0.30
    移åĬ¨
    0.29
    Activations Density 0.242%

    No Known Activations