© 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. 111919
    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
     ache
    -0.25
     åĪ
    -0.25
    iendo
    -0.25
     acute
    -0.25
    æ¡ĵ
    -0.25
    å¡«
    -0.24
    ry
    -0.24
    æŁIJç§į
    -0.23
     конÑģÑĤÑĢÑĥкÑĨи
    -0.23
    utta
    -0.23
    POSITIVE LOGITS
    ograd
    0.30
    &display
    0.28
    sheets
    0.27
    olders
    0.27
    ä¹Łä¸įä¾ĭå¤ĸ
    0.26
    çļ
    0.26
     ÑģкаÑĩ
    0.25
    夫
    0.25
    ).__
    0.24
    åıijæĶ¾
    0.24
    Activations Density 0.005%

    No Known Activations

    This feature has no known activations.