© 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. 23-TRANSCODER-HP
    7. 23441
    Prev
    Next
    INDEX
    Explanations

    Multiplication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    abs
    -0.28
    assen
    -0.27
    èĽ®
    -0.26
    å¿ĺ
    -0.26
    uous
    -0.26
    utation
    -0.25
    ione
    -0.25
    Ãło
    -0.25
    å°±æľī
    -0.25
    ulant
    -0.25
    POSITIVE LOGITS
     compared
    0.28
     disadvantage
    0.27
     *(*
    0.27
    AFP
    0.26
    çļĦä¼ĺåĬ¿
    0.25
     advantages
    0.25
     traditionally
    0.24
    好å¤Ħ
    0.24
     detriment
    0.24
     advantage
    0.24
    Activations Density 0.007%

    No Known Activations