© 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. 97725
    Prev
    Next
    INDEX
    Explanations

    Auxiliary verbs

    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
    ether
    -0.27
    breaker
    -0.27
    gram
    -0.26
    Submit
    -0.26
    æĶ¹éĢł
    -0.25
    ramid
    -0.25
    Others
    -0.25
    hatt
    -0.25
    ement
    -0.25
    ãģĵãģĨ
    -0.25
    POSITIVE LOGITS
     everywhere
    0.29
    åħ¬åı¸ç«łç¨ĭ
    0.27
    orts
    0.27
    uve
    0.27
    swers
    0.25
    pler
    0.24
    èģ¯
    0.24
    wiÄĻksz
    0.24
    æĹłåı¯
    0.24
    pei
    0.23
    Activations Density 0.007%

    No Known Activations