© 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. 19477
    Prev
    Next
    INDEX
    Explanations

    Names starting with "Mol/Wol"

    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
    enton
    -0.26
    åijĬè¯ī她
    -0.26
    autoload
    -0.26
    ÑĮеÑĢ
    -0.25
    ENT
    -0.25
    _DI
    -0.24
    rons
    -0.24
    YNAM
    -0.24
    èĩªåĬ¨åĮĸ
    -0.24
    ÑİÑīиÑħ
    -0.24
    POSITIVE LOGITS
    å§ĭ
    0.27
     Starts
    0.26
    ker
    0.26
    代表
    0.25
     Hear
    0.25
    uploader
    0.24
     monstr
    0.23
    .curve
    0.23
     representative
    0.23
     Relief
    0.23
    Activations Density 0.004%

    No Known Activations