© 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. 98354
    Prev
    Next
    INDEX
    Explanations

    Text snippets

    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
    atoire
    -0.28
    é£İåIJ¹
    -0.26
    æĪij们å°Ĩ
    -0.26
    utters
    -0.25
     rop
    -0.24
     blames
    -0.24
    ç»ĻæĤ¨
    -0.24
     replaced
    -0.24
     skipped
    -0.23
    ä»ĸ认为
    -0.23
    POSITIVE LOGITS
     COPYING
    0.28
     catch
    0.26
     poster
    0.25
    翻身
    0.25
    èį¥
    0.24
    egt
    0.24
    aste
    0.24
    poster
    0.23
     Tit
    0.23
    -striped
    0.23
    Activations Density 0.006%

    No Known Activations