© 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. 25-TRANSCODER-HP
    7. 108277
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦âĢ¦âĢ¦âĢ¦
    -0.27
     agr
    -0.26
    ÑģÑĥж
    -0.26
    })();
    -0.25
     ag
    -0.25
    áĢĦ
    -0.25
     equival
    -0.25
     coaching
    -0.25
    guid
    -0.24
     Twig
    -0.24
    POSITIVE LOGITS
    èĩªçĦ¶èµĦæºIJ
    0.30
    æįº
    0.29
     spat
    0.29
    æ¸ĹéĢı
    0.29
    é«ĺ强度
    0.28
     hell
    0.27
     opendir
    0.27
     filmer
    0.27
    ADVERTISEMENT
    0.27
    át
    0.26
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.