© 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. 113169
    Prev
    Next
    INDEX
    Explanations

    family relations

    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
    çŃĶåį·
    -0.27
    ilig
    -0.26
    æĸĻ
    -0.26
    olest
    -0.25
    æ¹ĥ
    -0.24
    öt
    -0.24
    æ¨ĺ
    -0.24
    <<<<
    -0.24
     apologies
    -0.23
    аниз
    -0.23
    POSITIVE LOGITS
    éŃĶ
    0.27
    éŃĶæľ¯
    0.26
    cken
    0.26
     bypass
    0.24
    ITUDE
    0.24
     Yard
    0.24
     Thomas
    0.24
    .adjust
    0.23
     jam
    0.23
     Fit
    0.23
    Activations Density 0.008%

    No Known Activations