© 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. 130532
    Prev
    Next
    INDEX
    Explanations

    Legal documents

    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
    uga
    -0.25
    aphrag
    -0.24
    è¯Ŀ
    -0.24
    iska
    -0.24
    iola
    -0.24
     Phonetic
    -0.23
     Guth
    -0.23
    effects
    -0.23
    æij©
    -0.23
     ngu
    -0.23
    POSITIVE LOGITS
     pro
    0.28
     exc
    0.25
    ç¼ł
    0.24
     autonom
    0.23
     promising
    0.23
    æµľ
    0.23
    .setPreferredSize
    0.23
    z
    0.23
     verse
    0.23
     Rab
    0.22
    Activations Density 0.061%

    No Known Activations