© 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. 18876
    Prev
    Next
    INDEX
    Explanations

    Construction and technical descriptions

    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
    ston
    -0.29
    è°¤
    -0.28
    é²ĭ
    -0.26
     units
    -0.26
    flutter
    -0.25
     gated
    -0.25
    çĦļ
    -0.24
    brown
    -0.24
    >Delete
    -0.24
    æĿŀ
    -0.24
    POSITIVE LOGITS
     Machine
    0.31
    Packages
    0.29
    machine
    0.29
    伦
    0.28
    Machine
    0.28
     machine
    0.27
    æľºåĻ¨
    0.26
     MACHINE
    0.26
    inery
    0.25
    é«ĺéĢŁ
    0.25
    Activations Density 0.305%

    No Known Activations