© 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. 41598
    Prev
    Next
    INDEX
    Explanations

    negative impacts

    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
    layouts
    -0.27
     layouts
    -0.26
     packed
    -0.26
    jac
    -0.26
    æ¸ĹéĢı
    -0.25
    à¸Ħา
    -0.25
    formats
    -0.25
    èĭį
    -0.25
    æľĿ
    -0.24
    _ro
    -0.24
    POSITIVE LOGITS
     anthrop
    0.36
     negative
    0.31
     adverse
    0.30
    è´Ł
    0.29
    Anth
    0.29
    è¦ģæ¯Ķ
    0.28
    ä¸įèī¯
    0.28
     quadrant
    0.28
    çĢij
    0.28
     negatives
    0.28
    Activations Density 0.001%

    No Known Activations