© 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. 130232
    Prev
    Next
    INDEX
    Explanations

    software license/modification

    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
    ?
    -0.31
    Network
    -0.28
    ...
    -0.28
    çļĦåĬĽéĩı
    -0.28
    éĹ»
    -0.27
      ↵
    -0.27
    è½»
    -0.27
    亲
    -0.26
    ?!
    -0.26
    !
    -0.26
    POSITIVE LOGITS
     :↵↵↵↵
    0.34
    "č↵č↵č↵
    0.28
    uja
    0.26
    ä¾ij
    0.25
     ;č↵č↵
    0.24
    ://%
    0.24
    æĸ°çļĦä¸Ģ
    0.24
     grade
    0.23
    ://"
    0.23
    ":č↵
    0.23
    Activations Density 0.007%

    No Known Activations