© 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. 88023
    Prev
    Next
    INDEX
    Explanations

    Numbers

    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
    ÄĮ
    -0.26
    /plain
    -0.26
    orth
    -0.25
     Tmax
    -0.25
    æѦåĬŁ
    -0.24
    _ASM
    -0.23
    _TD
    -0.23
    æĸ°ä¸ī
    -0.23
     admit
    -0.23
     Fuller
    -0.23
    POSITIVE LOGITS
    itect
    0.28
    夹
    0.27
    лага
    0.26
    Er
    0.25
    éĤĤ
    0.25
    ups
    0.24
     vá
    0.24
    ä»Ķç»Ĩ
    0.24
    å®ŀåľ°
    0.24
    å·©
    0.23
    Activations Density 0.014%

    No Known Activations