© 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. 20-TRANSCODER-HP
    7. 142154
    Prev
    Next
    INDEX
    Explanations

    achieve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é¹Ĭ
    -0.26
    bots
    -0.26
    avis
    -0.25
     quo
    -0.25
    glob
    -0.24
    ä½ĵéĩı
    -0.24
    avenport
    -0.24
    以å¤ĸ
    -0.24
    ä¸įåľ¨
    -0.24
    ä¸įåľ¨ä¹İ
    -0.24
    POSITIVE LOGITS
    Ĥ¬
    0.29
    æ·¦
    0.27
    roud
    0.25
    ĭè¯ķ
    0.25
     meaningful
    0.25
    conto
    0.25
    gar
    0.25
    оÑĩнÑĭй
    0.25
    riendly
    0.24
     conflicting
    0.24
    Activations Density 13.389%

    No Known Activations