© 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. 98853
    Prev
    Next
    INDEX
    Explanations

    to

    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
     myself
    -0.31
    çĻ¾ä¸ĩ
    -0.26
    Formatting
    -0.26
    åĽłä¸ºæĪij
    -0.26
    æīĢ以æĪij
    -0.25
     ourselves
    -0.25
    对æĪij
    -0.25
    帮æĪij
    -0.25
    æĪijçŁ¥éģĵ
    -0.25
    mmas
    -0.25
    POSITIVE LOGITS
    æѤæŶ
    0.26
    è¿Ļç§į
    0.26
    achten
    0.24
     Yates
    0.24
     fraternity
    0.24
    .jasper
    0.23
    éĺ´å½±
    0.23
    antino
    0.23
    -rec
    0.23
    è¿Ļç±»
    0.23
    Activations Density 0.010%

    No Known Activations