© 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. 18-TRANSCODER-HP
    7. 88993
    Prev
    Next
    INDEX
    Explanations

    Technical excerpts from online sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     switch
    -0.25
    èIJĿ
    -0.25
     loc
    -0.24
    hift
    -0.24
    igans
    -0.24
     dazu
    -0.23
     met
    -0.23
     case
    -0.23
     locus
    -0.23
    ä¾Ī
    -0.23
    POSITIVE LOGITS
    grim
    0.28
    è§Ħ模æľĢ大
    0.27
     ÑģкоÑĢо
    0.26
     discredit
    0.26
     ALPHA
    0.26
     bitterly
    0.25
     Singular
    0.25
    çļĦé£İéĻ©
    0.24
    ãģ¤ãģį
    0.24
    ://'
    0.24
    Activations Density 14.013%

    No Known Activations