© 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. 19217
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

    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
     mask
    -0.27
    åģ¥åº·æĪIJéķ¿
    -0.27
    Mask
    -0.26
    shed
    -0.25
     autos
    -0.25
     bask
    -0.25
    domains
    -0.25
     helmet
    -0.25
     bitmask
    -0.24
    ä¼ŀ
    -0.24
    POSITIVE LOGITS
    ToDevice
    0.28
    ç³Ł
    0.26
    NetMessage
    0.26
     Dough
    0.26
     Erin
    0.25
    aggio
    0.25
    èĥ½éĩı
    0.24
     Erg
    0.24
    æĥħ
    0.24
     stealing
    0.24
    Activations Density 1.525%

    No Known Activations