© 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. 23335
    Prev
    Next
    INDEX
    Explanations

    vowel sounds with trailing punctuation

    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
    蹶
    -0.09
    خار
    -0.09
     Matte
    -0.09
    sic
    -0.09
    é¢ľ
    -0.08
    _ln
    -0.08
    standen
    -0.08
    è¿ĻåĿĹ
    -0.08
    igte
    -0.08
     ìĬ¤ìĬ¤
    -0.08
    POSITIVE LOGITS
    å¾Ĵ
    0.10
    象
    0.09
    endir
    0.08
    ç¿ķ
    0.08
    åłªç§°
    0.08
    èµłéĢģ
    0.08
    éģIJ
    0.08
    è¶ħè¿ĩäºĨ
    0.08
    çİ»
    0.08
    proto
    0.08
    Activations Density 0.016%

    No Known Activations