© 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. 18158
    Prev
    Next
    INDEX
    Explanations

    File extensions

    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
    ãģªãĤĭ
    -0.27
    ви
    -0.27
    :Get
    -0.25
     onTouch
    -0.25
    ÑĪка
    -0.24
    æľīéĴ±
    -0.24
    :Add
    -0.24
     getAddress
    -0.24
    ulu
    -0.24
    :variables
    -0.23
    POSITIVE LOGITS
    .h
    0.48
    .*,
    0.47
    .s
    0.46
    .f
    0.44
    .l
    0.44
    .x
    0.43
    \.
    0.43
    .z
    0.43
    .j
    0.42
    .n
    0.42
    Activations Density 20.899%

    No Known Activations