© 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. 95646
    Prev
    Next
    INDEX
    Explanations

    movement and direction

    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
    ioned
    -0.29
    ÅĽ
    -0.29
    iaux
    -0.28
    ãĥIJãĥĥãĤ¯
    -0.27
    å£ij
    -0.26
    bread
    -0.26
    inge
    -0.26
    .converter
    -0.25
     móc
    -0.25
     Gingrich
    -0.24
    POSITIVE LOGITS
    缮çļĦåľ°
    0.30
     anywhere
    0.28
     their
    0.28
     somewhere
    0.28
    ä»ĸåľ¨
    0.28
    -stage
    0.28
    该
    0.27
    æ²¾
    0.27
     the
    0.27
     Fam
    0.27
    Activations Density 0.884%

    No Known Activations