© 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. 31-TRANSCODER-HP
    7. 18230
    Prev
    Next
    INDEX
    Explanations

    ov, vine

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fi
    -0.33
    cur
    -0.31
    æĸ§
    -0.31
    fi
    -0.31
    DM
    -0.28
    奴
    -0.26
    dm
    -0.26
    ·»
    -0.26
    ufen
    -0.26
     cur
    -0.25
    POSITIVE LOGITS
     opport
    0.28
    piel
    0.27
    eled
    0.27
    çļ®
    0.26
    olley
    0.26
    erton
    0.26
    ijľ
    0.26
    ä¸ķ
    0.26
    neys
    0.26
    aly
    0.26
    Activations Density 0.004%

    No Known Activations