© 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. 89624
    Prev
    Next
    INDEX
    Explanations

    still

    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
     aqui
    -0.28
     заб
    -0.28
    å¿ĺè®°äºĨ
    -0.27
    .basic
    -0.27
    Americ
    -0.27
    åıij表
    -0.26
    .mx
    -0.26
    .Big
    -0.26
    tÃł
    -0.26
    enza
    -0.25
    POSITIVE LOGITS
    operative
    0.24
    æľīèī²
    0.24
    InSection
    0.24
    è¯ij
    0.24
    гад
    0.23
    cdr
    0.23
    è¡Ħ
    0.23
    odu
    0.23
    åľ¨åħ¶
    0.23
    ous
    0.23
    Activations Density 15.967%

    No Known Activations