© 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. 30-TRANSCODER-HP
    7. 96660
    Prev
    Next
    INDEX
    Explanations

    academic degrees

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    boxes
    -0.33
    esses
    -0.28
    ’S
    -0.28
    boxed
    -0.25
    Trip
    -0.25
    ibli
    -0.25
    æĹ¥æĬ¥è®°èĢħ
    -0.25
     Ladies
    -0.25
    æĮĩæłĩ
    -0.24
    RTC
    -0.24
    POSITIVE LOGITS
    lea
    0.28
    le
    0.26
     kötü
    0.26
    åѦ
    0.26
    ais
    0.25
    ole
    0.24
    issance
    0.24
    ])[
    0.24
    วาà¸ĩ
    0.24
     ratio
    0.24
    Activations Density 0.110%

    No Known Activations