© 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. 32-TRANSCODER-HP
    7. 42302
    Prev
    Next
    INDEX
    Explanations

    an

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡ĮåĬ¨è®¡åĪĴ
    -0.30
    aksi
    -0.28
     createAction
    -0.27
     attacked
    -0.26
    ActionResult
    -0.26
    æĿijåħļæĶ¯éĥ¨
    -0.25
     addAction
    -0.24
    æīĵä»Ĺ
    -0.24
    æ´»åĬ¨
    -0.24
    atk
    -0.24
    POSITIVE LOGITS
     build
    0.37
     building
    0.33
     builds
    0.33
    build
    0.33
    Build
    0.33
    	build
    0.33
    omes
    0.32
    BUILD
    0.32
     BUILD
    0.31
     Build
    0.30
    Activations Density 0.001%

    No Known Activations