© 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. 87315
    Prev
    Next
    INDEX
    Explanations

    digits

    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
    躺çĿĢ
    -0.25
     py
    -0.24
    kÄħ
    -0.24
    ly
    -0.24
    åģļ人
    -0.24
     attraction
    -0.24
    ÑĢÑı
    -0.24
    çĦ¶æĺ¯
    -0.24
     Vander
    -0.24
    sales
    -0.23
    POSITIVE LOGITS
    失
    0.25
     motherboard
    0.24
    loss
    0.24
    çĬĬ
    0.24
    tober
    0.24
    ault
    0.23
     Medium
    0.23
    çŁ¥ãģ£ãģ¦
    0.23
    .todo
    0.23
    åĵ¥ä¼¦
    0.23
    Activations Density 0.006%

    No Known Activations