© 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. 112627
    Prev
    Next
    INDEX
    Explanations

    Names and organizations

    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
     sparing
    -0.30
    è¥ģ
    -0.28
    é«Ģ
    -0.27
    è··
    -0.26
    åĩºæīĭ
    -0.26
    ç»Īç»ĵ
    -0.25
    ç¾¹
    -0.25
     ÑģÑĭ
    -0.24
    :index
    -0.24
    çļ²
    -0.24
    POSITIVE LOGITS
    åħ¥åħļ
    0.36
    åħļåijĺ
    0.36
    宣
    0.30
    åħļ
    0.30
    çĪ±åĽ½ä¸»ä¹ī
    0.29
    åħļ建
    0.28
    åħļç»Ħç»ĩ
    0.28
    åħļåı²
    0.28
    çĮ®
    0.27
     Busy
    0.27
    Activations Density 0.001%

    No Known Activations