© 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. 19085
    Prev
    Next
    INDEX
    Explanations

    say "ation"

    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
     ins
    -0.28
     themselves
    -0.27
    áf
    -0.25
    ç¬ĭ
    -0.25
    Edit
    -0.25
    æµĭ
    -0.24
    ukt
    -0.24
    nets
    -0.23
    _ins
    -0.23
     unordered
    -0.23
    POSITIVE LOGITS
    åı£æ°Ķ
    0.34
    orgt
    0.27
     tá»ij
    0.27
    ervas
    0.26
    aja
    0.26
    饨
    0.26
    ERGY
    0.26
     Whip
    0.25
    TPL
    0.25
    ual
    0.24
    Activations Density 0.120%

    No Known Activations