© 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. 96755
    Prev
    Next
    INDEX
    Explanations

    in

    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
     sitting
    -0.33
     Sitting
    -0.32
     situated
    -0.32
     sit
    -0.30
    alse
    -0.30
    åĪĨå¸ĥåľ¨
    -0.29
    åģľ
    -0.28
     вне
    -0.28
     Sit
    -0.27
    ä½įæĸ¼
    -0.27
    POSITIVE LOGITS
     depress
    0.35
     Fres
    0.30
    slot
    0.29
     front
    0.29
     fronts
    0.27
    front
    0.27
    vern
    0.27
    arc
    0.26
     viewport
    0.26
     arc
    0.26
    Activations Density 0.894%

    No Known Activations