© 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. 128965
    Prev
    Next
    INDEX
    Explanations

    diverse 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
    jm
    -0.29
    çļĦçĭ¬çī¹
    -0.28
     uniqueness
    -0.25
    çļĦä¸Ģç§į
    -0.24
    itar
    -0.23
    çļĦéĴ±
    -0.23
     paj
    -0.23
    ãģ®ãģĮ
    -0.23
     Griff
    -0.23
    меÑīа
    -0.23
    POSITIVE LOGITS
    oku
    0.30
    endors
    0.27
    adients
    0.26
    ä¹ĭä¸Ģ
    0.25
    à¸Ħà¸Ń
    0.25
    ãĤīãģĽ
    0.25
    lst
    0.25
    aches
    0.25
    мÑı
    0.24
    YPES
    0.24
    Activations Density 0.013%

    No Known Activations