© 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. 128887
    Prev
    Next
    INDEX
    Explanations

    Scientific references

    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
     word
    -0.28
    ìĺ
    -0.27
    g
    -0.27
    #@
    -0.26
    aned
    -0.25
     stitching
    -0.25
    Ban
    -0.25
     monde
    -0.25
    SEP
    -0.24
    оÑĩек
    -0.24
    POSITIVE LOGITS
     ogl
    0.36
    _UNSIGNED
    0.28
    wares
    0.25
     Singles
    0.24
    ToProps
    0.24
    rif
    0.24
     synd
    0.24
     proven
    0.24
     <!--[
    0.24
    flater
    0.23
    Activations Density 0.005%

    No Known Activations