© 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. 27-TRANSCODER-HP
    7. 8698
    Prev
    Next
    INDEX
    Explanations

    grounding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     intersection
    -0.30
    cou
    -0.30
     merged
    -0.26
     horizon
    -0.26
    onders
    -0.26
    arness
    -0.26
    men
    -0.26
    asons
    -0.25
     intersections
    -0.25
     overlap
    -0.25
    POSITIVE LOGITS
    ç±į
    0.28
    åĵĨ
    0.27
    åĬŁå¾·
    0.26
    æľºä½ĵ
    0.26
    ä¸įæĿ¥
    0.25
    ldb
    0.25
    lug
    0.25
    ä¸įå¾Ĺ
    0.24
     shar
    0.24
    GameData
    0.24
    Activations Density 0.006%

    No Known Activations