© 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. 18544
    Prev
    Next
    INDEX
    Explanations

    complications and possibilities

    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
    è½»
    -0.32
    çħ
    -0.27
    pick
    -0.26
     picking
    -0.26
     picked
    -0.26
    ç¿¡
    -0.25
     pick
    -0.25
    è¼ķ
    -0.25
    azi
    -0.24
    aviolet
    -0.24
    POSITIVE LOGITS
     contributes
    0.30
    ibli
    0.28
    veyor
    0.26
    è´¡çĮ®
    0.26
    Contrib
    0.26
    LayoutPanel
    0.25
     contributor
    0.25
    æľī害
    0.25
    ibt
    0.24
    licative
    0.24
    Activations Density 1.881%

    No Known Activations