© 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. 63944
    Prev
    Next
    INDEX
    Explanations

    and

    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
     threads
    -0.28
     geld
    -0.28
     Held
    -0.27
    é¼İ
    -0.27
     Num
    -0.26
    æİĴ
    -0.26
    已达
    -0.25
    holds
    -0.25
    æĮģæľī
    -0.25
     realms
    -0.25
    POSITIVE LOGITS
    ç²¹
    0.27
    odef
    0.26
    åĶ¤
    0.25
    tout
    0.25
    AUSE
    0.25
    å¾ħéģĩ
    0.24
    ç©°
    0.24
    _printf
    0.24
    иÑĢов
    0.24
     Sinn
    0.24
    Activations Density 15.366%

    No Known Activations