© 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. 42376
    Prev
    Next
    INDEX
    Explanations

    P

    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
    说ä¸įåĩº
    -0.28
     tá»Ń
    -0.26
    èĪ·
    -0.26
    added
    -0.26
    leur
    -0.26
    les
    -0.25
     laat
    -0.25
    less
    -0.25
     observable
    -0.24
    æĬŁ
    -0.24
    POSITIVE LOGITS
     Anchor
    0.33
    ame
    0.28
    rup
    0.27
     Anch
    0.27
     anchors
    0.27
     amen
    0.27
    rollo
    0.26
    roller
    0.26
    emarks
    0.26
    vana
    0.26
    Activations Density 0.021%

    No Known Activations