© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 97264
    Prev
    Next
    INDEX
    Explanations

    march

    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
    Negative Logits
    sumer
    -0.26
    taire
    -0.26
    jection
    -0.26
    cao
    -0.25
    ction
    -0.25
    å¤ļä½Ļ
    -0.24
    isphere
    -0.24
    å¨ĺ家
    -0.24
     Unsure
    -0.24
    izzer
    -0.24
    POSITIVE LOGITS
    s
    0.35
     spo
    0.27
    le
    0.26
    y
    0.26
    sand
    0.26
    sse
    0.26
    วà¸Ļ
    0.25
    ime
    0.25
    rone
    0.25
    i
    0.25
    Activations Density 0.151%

    No Known Activations