© 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. 142242
    Prev
    Next
    INDEX
    Explanations

    Software and operating systems

    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
    å¼Ĭ
    -0.32
    æĹ¢æľī
    -0.31
    æĹ¢
    -0.29
     earliest
    -0.28
    çĥĪ
    -0.28
    storm
    -0.27
    æľĪä¸Ń
    -0.26
    older
    -0.25
    ToWorld
    -0.25
     evolved
    -0.25
    POSITIVE LOGITS
    ections
    0.29
    ÑĥменÑĤ
    0.26
    ulance
    0.25
    Sac
    0.25
    ->$
    0.24
    ponsor
    0.24
    <Value
    0.24
    aras
    0.24
    åIJģ
    0.24
     Sac
    0.23
    Activations Density 18.784%

    No Known Activations