© 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. 88208
    Prev
    Next
    INDEX
    Explanations

    code and software excerpts

    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
    izons
    -0.24
    borg
    -0.24
    inston
    -0.24
    side
    -0.23
    ecycle
    -0.23
    --)
    -0.23
     Glas
    -0.23
     Jupiter
    -0.23
     '^
    -0.23
     Soft
    -0.23
    POSITIVE LOGITS
    åı¦ä¸Ģç§į
    0.35
    该
    0.32
    åı¦ä¸Ģ个
    0.30
    该项
    0.30
    åı¦ä¸Ģ
    0.29
    æľªæĪIJ
    0.28
     another
    0.28
    éĤ£ä¸ª
    0.27
    åı¦ä¸ĢåįĬ
    0.27
    åıijè¾¾åĽ½å®¶
    0.26
    Activations Density 0.003%

    No Known Activations