© 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. 35187
    Prev
    Next
    INDEX
    Explanations

    from

    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
    ETHER
    -0.10
    bras
    -0.10
    å·²åľ¨
    -0.09
    rase
    -0.09
    ç»ĻåĩºäºĨ
    -0.09
    .assertThat
    -0.09
    legg
    -0.09
    iationException
    -0.09
    ulty
    -0.09
    launch
    -0.08
    POSITIVE LOGITS
    éķ¿è¿ľ
    0.08
    åİŁæľī
    0.08
    æĢĢæĬ±
    0.08
    çİ°æľī
    0.08
    é¦ĸä½į
    0.08
     surroundings
    0.08
    çİ°æľīçļĦ
    0.08
    åħīéĺ´
    0.08
    illon
    0.07
    带æĿ¥
    0.07
    Activations Density 0.019%

    No Known Activations