© 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. 12-TRANSCODER-HP
    7. 22669
    Prev
    Next
    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çļĦ人çī©
    -0.31
    isters
    -0.27
     vit
    -0.27
    isce
    -0.27
    ritt
    -0.27
     Hist
    -0.26
     Directorate
    -0.26
     perf
    -0.26
     Excell
    -0.25
    fv
    -0.25
    POSITIVE LOGITS
    sexual
    0.25
    amous
    0.25
    åľ©
    0.25
    æľŁ
    0.25
    ossal
    0.24
    åIJįæł¡
    0.24
     infr
    0.24
    lux
    0.24
    -chat
    0.23
    æIJ¶
    0.23
    Activations Density 0.036%

    No Known Activations