© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 129970
    Prev
    Next
    INDEX
    Explanations

    ischemia

    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
    Not in Any Lists

    No Comments

    Negative Logits
    %X
    -0.31
    ucked
    -0.28
    icts
    -0.27
    reh
    -0.27
    anax
    -0.26
    rays
    -0.26
    HIR
    -0.26
    æĮij
    -0.26
    æĸĩä¸Ń
    -0.25
     gu
    -0.25
    POSITIVE LOGITS
     suspicion
    0.33
    .neg
    0.29
    [np
    0.27
    theless
    0.26
    åĢ¾åIJij
    0.26
     suspicions
    0.25
    å«Įçĸij
    0.25
    ame
    0.25
    input
    0.24
     inputs
    0.24
    Activations Density 0.068%

    No Known Activations