© 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. 112576
    Prev
    Next
    INDEX
    Explanations

    and

    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
    amburger
    -0.28
     <![
    -0.28
    resco
    -0.26
     hitch
    -0.26
    arium
    -0.25
    çĻ¾ç§ij
    -0.25
    éĩįéĩį
    -0.24
    å½ķåıĸ
    -0.24
    .TabStop
    -0.24
    atform
    -0.24
    POSITIVE LOGITS
    并åIJij
    0.32
    并
    0.31
    说æĺ¯
    0.30
    并éĢļè¿ĩ
    0.29
    å¨ģ
    0.27
    并对
    0.26
     XF
    0.26
    éĥ½ä¼ļ
    0.26
     Experimental
    0.25
    åĩºäºİ
    0.25
    Activations Density 0.019%

    No Known Activations