© 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. 19192
    Prev
    Next
    INDEX
    Explanations

    proper nouns and code

    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
    udu
    -0.26
     çĶŁåij½åij¨æľŁ
    -0.26
    udi
    -0.26
    BOSE
    -0.25
     Belt
    -0.24
    æ¶Ł
    -0.24
     cooks
    -0.24
    æĺŁåħī
    -0.24
    ["_
    -0.24
    omen
    -0.24
    POSITIVE LOGITS
    客æĪ·æıIJä¾Ľ
    0.32
    çĶ¨æĪ·æıIJä¾Ľ
    0.26
    orny
    0.25
    XYZ
    0.25
    ź
    0.24
    _COLL
    0.23
    æ°¨éħ¸
    0.23
    迨
    0.23
    æŃĩ
    0.23
    ]+'
    0.23
    Activations Density 0.004%

    No Known Activations