© 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. 18306
    Prev
    Next
    INDEX
    Explanations

    valve

    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
    orsk
    -0.27
    ILA
    -0.27
    åIJ»
    -0.26
    losed
    -0.26
    nze
    -0.26
     Wage
    -0.25
    象
    -0.25
    åĽ¢
    -0.25
     Cro
    -0.24
    åĮĸ
    -0.24
    POSITIVE LOGITS
     arrangement
    0.32
     arrang
    0.27
    ç»Ħè£ħ
    0.26
    worm
    0.26
    æĭ¼åij½
    0.25
     arrangements
    0.25
     bowl
    0.25
    -mounted
    0.25
     memory
    0.25
    fish
    0.25
    Activations Density 1.845%

    No Known Activations