© 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. 112427
    Prev
    Next
    INDEX
    Explanations

    leagues

    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
     selves
    -0.30
    IRD
    -0.29
    ή
    -0.27
    xic
    -0.26
     Drum
    -0.26
    elves
    -0.25
     Circuit
    -0.24
     colleagues
    -0.24
     instituted
    -0.24
    æħ¥
    -0.24
    POSITIVE LOGITS
    opsis
    0.26
    çľģ
    0.26
    poons
    0.24
     Antar
    0.24
    å·¥å§Ķ
    0.23
    gain
    0.23
    éģĤ
    0.23
    atra
    0.23
    stras
    0.23
     mạng
    0.23
    Activations Density 0.029%

    No Known Activations