© 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. 129772
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
    аÑĢÑĮ
    -0.26
    omm
    -0.25
    åĶ®
    -0.23
    нÑĮ
    -0.23
    ondheim
    -0.23
    æĹħ游å±Ģ
    -0.23
    ¶ļ
    -0.23
    PointerType
    -0.23
    łģ
    -0.22
    段
    -0.22
    POSITIVE LOGITS
    elman
    0.27
    fen
    0.27
     Claude
    0.26
    ê°IJ
    0.24
    scape
    0.24
    æľŃ
    0.24
    jem
    0.24
     gar
    0.24
    von
    0.24
    shirt
    0.24
    Activations Density 0.003%

    No Known Activations