© 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. 57835
    Prev
    Next
    INDEX
    Explanations

    Residuals

    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
     true
    -0.44
    true
    -0.39
    羣
    -0.35
    羣æŃ£çļĦ
    -0.32
     verdade
    -0.32
    羣æŃ£
    -0.31
    _true
    -0.30
     True
    -0.29
    jah
    -0.29
    (true
    -0.28
    POSITIVE LOGITS
     residuals
    0.34
     residues
    0.34
     residual
    0.31
    æĪIJ为ä¸ŃåĽ½
    0.30
     influential
    0.29
    ç¿ħ
    0.28
    æ®ĭ
    0.28
    è½¬åŁºåĽł
    0.27
    CHA
    0.27
     residue
    0.26
    Activations Density 0.018%

    No Known Activations