© 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. 130382
    Prev
    Next
    INDEX
    Explanations

    :

    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
    йÑĤеÑģÑĮ
    -0.29
    tracts
    -0.29
    åIJİèĢħ
    -0.27
     PyErr
    -0.26
    Ns
    -0.26
    é¢ĺ主
    -0.25
    wargs
    -0.25
    esthes
    -0.25
    monthly
    -0.25
    ertainment
    -0.24
    POSITIVE LOGITS
    èĥ¥
    0.28
    缺
    0.26
    èĩ
    0.25
    \Bundle
    0.25
     Terms
    0.25
    羣æŃ£çļĦ
    0.24
    ||↵
    0.24
    -process
    0.24
     AUTHORS
    0.24
    ||
    0.23
    Activations Density 0.027%

    No Known Activations