© 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. 131218
    Prev
    Next
    INDEX
    Explanations

    Conversational/technical text snippets

    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
    (ln
    -0.28
    æ®ĵ
    -0.27
    .isPresent
    -0.27
    igner
    -0.27
    StateException
    -0.26
     lawful
    -0.26
    éĥ¨éĥ¨éķ¿
    -0.25
    }:${
    -0.25
    (strip
    -0.24
    çļij
    -0.24
    POSITIVE LOGITS
    åĢĴ
    0.29
    æĵį
    0.28
    èĦ±
    0.28
    次
    0.27
    å¥ī
    0.27
     Secondary
    0.26
    Cou
    0.26
    èİ«
    0.26
     Cou
    0.25
    æıĴ
    0.25
    Activations Density 0.020%

    No Known Activations