© 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. 97572
    Prev
    Next
    INDEX
    Explanations

    Generic, diverse text

    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
     einmal
    -0.26
     Raw
    -0.25
    once
    -0.25
    绣çŃ¹
    -0.24
     accum
    -0.23
    å®ŀå®ŀåľ¨åľ¨
    -0.22
     intox
    -0.22
    æīĢ以æĪij们
    -0.22
    ìºħ
    -0.22
     raw
    -0.22
    POSITIVE LOGITS
    venta
    0.26
    åĿĤ
    0.26
    人
    0.23
    atak
    0.23
    ège
    0.23
    ÇĶ
    0.23
    _coordinate
    0.23
    ¡°
    0.22
    antha
    0.22
    级åĪ«
    0.21
    Activations Density 0.010%

    No Known Activations