© 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. 88404
    Prev
    Next
    INDEX
    Explanations

    Colon and period

    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
    æ³¥åľŁ
    -0.30
    åŃĺåľ¨äºİ
    -0.28
     next
    -0.27
    arus
    -0.26
    çĹŀ
    -0.25
    æĭĶ
    -0.25
    <Scalar
    -0.25
    Cod
    -0.23
    èµ°åľ¨
    -0.23
    é¦ĸ页
    -0.23
    POSITIVE LOGITS
    _ang
    0.28
    饯
    0.27
    exact
    0.26
     LARGE
    0.26
     spotting
    0.25
    è¿ĩ
    0.25
    大å±Ģ
    0.25
    TeV
    0.24
     gran
    0.24
    Ļ¶
    0.24
    Activations Density 0.006%

    No Known Activations