© 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. 19298
    Prev
    Next
    INDEX
    Explanations

    mathematics and statistics

    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
    ances
    -0.35
    ance
    -0.31
    lify
    -0.29
    æĿ¼
    -0.27
    uality
    -0.27
    otate
    -0.27
    à¤ŀ
    -0.26
    -gap
    -0.26
    ilarity
    -0.26
    å§Ķä¼ļ
    -0.26
    POSITIVE LOGITS
    æľºæ¢°
    0.28
     Machines
    0.27
    Generated
    0.26
    emp
    0.26
    mh
    0.26
    åŁºçĿ£å¾Ĵ
    0.25
    mia
    0.25
     Engines
    0.24
    è§īå¾Ĺå¾Ī
    0.24
    nett
    0.24
    Activations Density 0.011%

    No Known Activations