© 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. 130003
    Prev
    Next
    INDEX
    Explanations

    Research and clinical settings

    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
    ears
    -0.27
    falls
    -0.25
    ANA
    -0.24
    åĨĻäºĨ
    -0.24
    /repository
    -0.23
    å£ħ
    -0.23
     оÑĤкÑĢÑĭва
    -0.23
     dõi
    -0.23
    ÅĪ
    -0.23
    ANE
    -0.23
    POSITIVE LOGITS
    ä¸įçŁ¥
    0.31
    åīª
    0.29
    edis
    0.29
    icer
    0.28
     relev
    0.28
    æ¨Ĭ
    0.26
    lin
    0.24
    æĸĩæĺİåŁİå¸Ĥ
    0.24
    两ç§į
    0.24
    adoras
    0.23
    Activations Density 0.017%

    No Known Activations