© 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. 130789
    Prev
    Next
    INDEX
    Explanations

    Unstructured texts

    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
    bff
    -0.25
     getNode
    -0.25
     Seed
    -0.24
     definitely
    -0.24
     Offers
    -0.23
    Known
    -0.23
    ardy
    -0.23
    LERÄ°
    -0.23
    Serve
    -0.22
    inally
    -0.22
    POSITIVE LOGITS
    ison
    0.26
    ä¸Ī夫
    0.26
    reload
    0.24
    EÄŀ
    0.24
    è¡®
    0.24
    ç¢ļ
    0.24
    oom
    0.24
    åIJĦè¡ĮåIJĦä¸ļ
    0.23
    çļĦèīºæľ¯
    0.23
    DER
    0.23
    Activations Density 0.000%

    No Known Activations