© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 2558
    Prev
    Next
    INDEX
    Explanations

    Frontend Developer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¡·
    -0.10
    roc
    -0.09
    类产åĵģ
    -0.09
    临港
    -0.09
    è¡Į车
    -0.09
     Plat
    -0.09
    å¹¿åľº
    -0.09
    oding
    -0.09
    -pass
    -0.08
    \Bridge
    -0.08
    POSITIVE LOGITS
    éĻ²
    0.10
    åIJĮæŶè¿ĺ
    0.08
     tạp
    0.08
    urf
    0.08
    仵
    0.08
    eros
    0.08
     tail
    0.08
    å°ıäºĭ
    0.08
    laÅŁ
    0.08
    /down
    0.08
    Activations Density 0.010%

    No Known Activations