© 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. 18894
    Prev
    Next
    INDEX
    Explanations

    NASA

    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
     mission
    -0.50
     missions
    -0.41
    mission
    -0.35
     Mission
    -0.34
    Mission
    -0.34
    ä»»åĬ¡
    -0.32
     satellites
    -0.32
    MISSION
    -0.32
    åį«æĺŁ
    -0.31
    missions
    -0.30
    POSITIVE LOGITS
    æĦŁ
    0.30
    åŁł
    0.30
    aret
    0.30
     Randolph
    0.28
    aves
    0.28
    remote
    0.27
    walker
    0.27
    è¿ľç¨ĭ
    0.27
    getc
    0.26
    uft
    0.26
    Activations Density 18.195%

    No Known Activations