© 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. 112066
    Prev
    Next
    INDEX
    Explanations

    shocked

    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
    大家éĥ½
    -0.40
     everybody
    -0.37
     everyone
    -0.36
    大家
    -0.32
    èªįçĤº
    -0.32
    éĥ½è§īå¾Ĺ
    -0.31
    大家éĥ½åľ¨
    -0.30
     Everybody
    -0.30
    认为
    -0.30
    éĥ½è®¤ä¸º
    -0.29
    POSITIVE LOGITS
    使æĪij
    0.32
     unit
    0.30
    ity
    0.27
    itional
    0.27
     Carry
    0.27
    é«ĺ楼
    0.25
    unit
    0.25
    让æĪij
    0.24
    æĸ°åĮº
    0.24
    comp
    0.24
    Activations Density 0.015%

    No Known Activations