© 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. 20-TRANSCODER-HP
    7. 142146
    Prev
    Next
    INDEX
    Explanations

    latest

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itti
    -0.28
    logg
    -0.27
    attachments
    -0.27
    _attachments
    -0.27
    erie
    -0.26
    otec
    -0.25
    ç¼ĸ
    -0.25
    riages
    -0.24
    cle
    -0.24
    RIPT
    -0.24
    POSITIVE LOGITS
    æīĢåľ¨
    0.27
    ÑIJ
    0.25
    heits
    0.24
    ળ
    0.24
    æīĢåľ¨åľ°
    0.23
    -news
    0.23
     news
    0.23
    æ¯ıä½į
    0.23
     ctypes
    0.23
    SYM
    0.23
    Activations Density 4.226%

    No Known Activations