© 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. 87689
    Prev
    Next
    INDEX
    Explanations

    Societal systems and regulations

    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
    æѤç§į
    -0.26
     bạc
    -0.25
    iola
    -0.25
    леж
    -0.25
     altogether
    -0.25
    讲æķħäºĭ
    -0.25
    çļĦæķ´ä½ĵ
    -0.25
    没æľīæĥ³åĪ°
    -0.24
    niejs
    -0.24
    çļĦæĥħ绪
    -0.24
    POSITIVE LOGITS
     trough
    0.31
    one
    0.28
     support
    0.26
    own
    0.25
    omal
    0.25
    ally
    0.24
     sunday
    0.24
    bourne
    0.24
    ows
    0.23
    ãĤį
    0.23
    Activations Density 0.011%

    No Known Activations