© 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. 88465
    Prev
    Next
    INDEX
    Explanations

    Titles of creative works

    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
    orde
    -0.29
    ức
    -0.26
    ocard
    -0.24
    ÅĽcie
    -0.24
    afen
    -0.23
    egen
    -0.23
     Duis
    -0.23
    dana
    -0.23
    duit
    -0.23
     Damen
    -0.23
    POSITIVE LOGITS
    åĽ¾ä¹¦
    0.27
    ISBN
    0.26
    éĩĩè´Ń
    0.24
    æľ¬ä¹¦
    0.24
     aup
    0.23
    é«ĺæ½®
    0.23
    .timeout
    0.23
     superv
    0.23
    已达
    0.23
     Phần
    0.23
    Activations Density 0.082%

    No Known Activations