© 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. 88273
    Prev
    Next
    INDEX
    Explanations

    racial

    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
    illian
    -0.34
    /or
    -0.32
    /il
    -0.31
    /↵↵↵
    -0.30
    /OR
    -0.29
    /
    -0.28
     lite
    -0.27
    gia
    -0.27
    /Object
    -0.27
    aiser
    -0.26
    POSITIVE LOGITS
    ç»Ī
    0.27
     enim
    0.26
    .hasNext
    0.25
    åĴĮåħ¶ä»ĸ
    0.25
    eg
    0.25
    æİĮéŨ
    0.24
    è´
    0.24
    ews
    0.23
    ï¼ļ"
    0.23
    :"
    0.23
    Activations Density 0.012%

    No Known Activations