© 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. 22-TRANSCODER-HP
    7. 98149
    Prev
    Next
    INDEX
    Explanations

    Academic, technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸İæѤ
    -0.26
    corr
    -0.25
    sched
    -0.24
    uj
    -0.24
    ErrorMessage
    -0.24
    éĤ£äºĽ
    -0.24
    лÑı
    -0.23
    adium
    -0.23
     Hear
    -0.23
     built
    -0.23
    POSITIVE LOGITS
    eties
    0.28
    uries
    0.27
    arian
    0.27
    æīĢåľ¨
    0.25
    -lite
    0.25
     Chairs
    0.25
    æĥħåĨµè¿Ľè¡Į
    0.25
    anted
    0.24
    uffer
    0.24
    çŁ³å¤´
    0.24
    Activations Density 0.226%

    No Known Activations