© 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. 25-TRANSCODER-HP
    7. 107979
    Prev
    Next
    INDEX
    Explanations

    Code and software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĵįä½ľ
    -0.30
    ç»Ĩ
    -0.27
    æľ«
    -0.27
    个交æĺĵ
    -0.26
    xbc
    -0.26
     Mach
    -0.26
    èį·
    -0.24
    compass
    -0.24
    ighth
    -0.24
    -render
    -0.23
    POSITIVE LOGITS
    Contained
    0.28
     wards
    0.25
    ocks
    0.25
    å¸ĮæľĽèĥ½
    0.24
    ystems
    0.24
    nip
    0.24
    (console
    0.24
     phosphory
    0.24
     valueForKey
    0.23
    æ²±
    0.23
    Activations Density 0.110%

    No Known Activations