© 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. 86861
    Prev
    Next
    INDEX
    Explanations

    citrus

    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
     gap
    -0.27
    ÑģÑĥд
    -0.25
    -gap
    -0.25
    etermination
    -0.25
    ToDevice
    -0.24
     gaps
    -0.24
    æ£į
    -0.23
    éĴ»çŁ³
    -0.23
    ä¹łæĥ¯
    -0.23
    structures
    -0.23
    POSITIVE LOGITS
    ality
    0.35
    æĹħ游度åģĩ
    0.26
    ransition
    0.25
    rado
    0.24
    ning
    0.24
    ron
    0.24
    èĮħ
    0.24
    asting
    0.24
    tery
    0.24
    ennen
    0.24
    Activations Density 0.375%

    No Known Activations