© 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. 129861
    Prev
    Next
    INDEX
    Explanations

    Parentheses and conjunctions

    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
    æ¼ī
    -0.27
    ople
    -0.27
    encer
    -0.25
    conti
    -0.25
    æ»´
    -0.25
    çģĮ
    -0.24
    温åĴĮ
    -0.24
     Zar
    -0.24
    -links
    -0.23
    quirer
    -0.23
    POSITIVE LOGITS
     Dorm
    0.23
     Vere
    0.23
     Ball
    0.23
     glossy
    0.23
    让å®ĥ
    0.22
    findFirst
    0.22
    coil
    0.22
    çIJĨ
    0.22
    IC
    0.22
     dock
    0.22
    Activations Density 0.049%

    No Known Activations