© 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. 129859
    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
    å¾Īåı¯èĥ½
    -0.25
    åİŁåĪĻä¸Ĭ
    -0.25
    vel
    -0.25
    ä¸ĢåĪĢ
    -0.24
    hell
    -0.24
     Day
    -0.23
    beat
    -0.23
     prol
    -0.23
    ublisher
    -0.23
    YE
    -0.23
    POSITIVE LOGITS
    ))^
    0.26
    æĮĤçīĮ
    0.24
    à¸Ħม
    0.24
    çµIJ
    0.24
    etically
    0.24
    èijµ
    0.24
    оÑģÑĮ
    0.23
    utilus
    0.23
    eldon
    0.23
    oup
    0.23
    Activations Density 0.008%

    No Known Activations

    This feature has no known activations.