© 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. 19521
    Prev
    Next
    INDEX
    Explanations

    dis prefix

    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
     priesthood
    -0.30
     hedge
    -0.29
     assured
    -0.28
    oland
    -0.28
     distributed
    -0.27
    çķĻå®Ī
    -0.27
     scratch
    -0.27
    ular
    -0.26
    åĪĨæķ£
    -0.26
    bara
    -0.26
    POSITIVE LOGITS
    æĶ¶
    0.29
    icamente
    0.28
    _stdio
    0.28
    åIJĥ
    0.28
    usz
    0.27
     condition
    0.26
    çĶŁãģ¾ãĤĮ
    0.26
     qualification
    0.26
    ç¦ģ
    0.25
    å½¢
    0.25
    Activations Density 0.007%

    No Known Activations