© 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. 63319
    Prev
    Next
    INDEX
    Explanations

    data size

    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
    adar
    -0.29
    icularly
    -0.26
    è¡¥åħħ
    -0.26
     **/č↵
    -0.26
    ä¸ĺ
    -0.26
    **č↵
    -0.25
    .HandlerFunc
    -0.25
     recogn
    -0.25
    åIJį为
    -0.24
     '''č↵
    -0.24
    POSITIVE LOGITS
    稼
    0.27
    æĪ·åı£
    0.27
    ree
    0.26
     Exclusive
    0.26
    ìĦł
    0.26
    æķĪæŀľåĽ¾
    0.25
    ICS
    0.25
    Degree
    0.25
     Vict
    0.24
    oley
    0.24
    Activations Density 3.964%

    No Known Activations