© 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. 99028
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    ichel
    -0.27
    ploy
    -0.25
    ITHER
    -0.25
    htar
    -0.24
     industrial
    -0.24
    agento
    -0.23
     whoever
    -0.23
    æľīä½ķ
    -0.23
    iet
    -0.23
    次ä¼ļè®®
    -0.23
    POSITIVE LOGITS
    roup
    0.26
    ä¾Ŀèµĸ
    0.26
    nock
    0.24
    åı£æ°´
    0.24
    (Grid
    0.24
    æ°ijå¿ĥ
    0.24
    aming
    0.23
     Package
    0.23
     curls
    0.23
    AxisAlignment
    0.23
    Activations Density 0.010%

    No Known Activations