© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 88657
    Prev
    Next
    INDEX
    Explanations

    Diverse text

    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
    ;'>
    -0.28
    oref
    -0.28
    亶
    -0.25
     Rack
    -0.24
    },'
    -0.24
    ;'
    -0.24
    ;\">
    -0.23
    áveis
    -0.23
    ãĢįãĢĮ
    -0.23
    ubar
    -0.23
    POSITIVE LOGITS
    CS
    0.30
    缺åı£
    0.25
    å°±æĺ¯è¿Ļæł·
    0.24
     esac
    0.24
     ÑģообÑīаеÑĤ
    0.23
    è¯Ĵ
    0.22
    _js
    0.22
     dam
    0.22
    æ³Ĺ
    0.22
    åĢ¼å¾Ĺä¸ĢæıIJ
    0.22
    Activations Density 0.004%

    No Known Activations