© 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. 130001
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    vore
    -0.29
    ÑĥÑĩа
    -0.28
     His
    -0.25
    ç®ĵ
    -0.24
    è±¢
    -0.24
    å¼ĢåıijåĪ©çĶ¨
    -0.24
    èĦ¾èĥĥ
    -0.24
    çŁ¥éģĵèĩªå·±
    -0.24
    oop
    -0.24
     Abel
    -0.24
    POSITIVE LOGITS
    åŀ«
    0.32
     till
    0.28
     load
    0.28
     reste
    0.28
     HttpResponseMessage
    0.27
    快讯
    0.26
     rest
    0.26
     regs
    0.26
    oxetine
    0.26
    éĺ´
    0.25
    Activations Density 0.015%

    No Known Activations

    This feature has no known activations.