© 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. 97356
    Prev
    Next
    INDEX
    Explanations

    comparing values

    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
     Brill
    -0.28
    ç«
    -0.27
    ear
    -0.26
    ä¸ĬãģĮãĤĬ
    -0.26
    osci
    -0.25
    .alias
    -0.25
    mpp
    -0.25
    chio
    -0.25
    urers
    -0.25
    mand
    -0.24
    POSITIVE LOGITS
    inz
    0.27
    åľ°å½¢
    0.25
    è¯į
    0.25
     rubble
    0.24
     generalize
    0.24
     rage
    0.23
     comprehension
    0.23
    erals
    0.23
    rene
    0.23
     Nev
    0.23
    Activations Density 0.007%

    No Known Activations