© 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. 42564
    Prev
    Next
    INDEX
    Explanations

    code, copyright

    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
     primary
    -0.27
    éĻĮ
    -0.26
    pine
    -0.26
    anas
    -0.25
     effectively
    -0.25
     ultr
    -0.25
    utton
    -0.24
    elia
    -0.24
    eli
    -0.24
    stances
    -0.24
    POSITIVE LOGITS
    æķıæĦŁ
    0.30
    çĽĸ
    0.30
    èĵĭ
    0.29
    çķ¢æ¥Ń
    0.27
    icot
    0.27
    ITCH
    0.27
    åī©
    0.26
    char
    0.25
     Triumph
    0.25
    æij©
    0.25
    Activations Density 0.009%

    No Known Activations