© 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. 23182
    Prev
    Next
    INDEX
    Explanations

    computer internet activity

    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
    arring
    -0.28
    /browse
    -0.27
    æĥ³æ³ķ
    -0.27
    ATUS
    -0.27
     widest
    -0.26
    é¦ĸåıij
    -0.26
     toured
    -0.26
    èĦ©
    -0.25
    æģķ
    -0.25
     cured
    -0.25
    POSITIVE LOGITS
    abaj
    0.26
    ä¸ģ
    0.26
    '),↵↵
    0.26
    æ¡Ī
    0.25
     citizen
    0.24
    amen
    0.24
    uer
    0.24
    '),č↵
    0.23
    imentary
    0.23
    æĬĬ她
    0.23
    Activations Density 0.000%

    No Known Activations