© 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. 88608
    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
    æıī
    -0.26
    isol
    -0.25
    çķ¸
    -0.24
    orrent
    -0.24
    alous
    -0.24
    gorit
    -0.24
    èĴĭ
    -0.24
    âľ©
    -0.24
    buckets
    -0.23
    bung
    -0.23
    POSITIVE LOGITS
    ä¸Ŀ绸ä¹ĭè·¯
    0.27
    èµIJ
    0.27
    phere
    0.27
    ming
    0.27
    尤为
    0.26
    s
    0.25
    '
    0.25
    gen
    0.25
    esting
    0.25
     ally
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.