© 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. 18991
    Prev
    Next
    INDEX
    Explanations

    Non-English words

    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
    cross
    -0.34
     cross
    -0.29
    isable
    -0.28
    rena
    -0.28
     residuals
    -0.27
     Cross
    -0.27
    -cross
    -0.27
    ross
    -0.26
    åłĤ
    -0.26
    Cross
    -0.25
    POSITIVE LOGITS
    ä¸ĭè¡Į
    0.26
    缸åıį
    0.26
    äºĨ解
    0.25
    CO
    0.25
    æĿł
    0.24
    Boxes
    0.24
    èĬ¯çīĩ
    0.24
    çŁĽçĽ¾
    0.24
    anceled
    0.24
    éĶļ
    0.24
    Activations Density 0.971%

    No Known Activations