© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36558
    Prev
    Next
    INDEX
    Explanations

    after 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
    ftware
    -0.11
    IGINAL
    -0.10
    çļĦ年轻人
    -0.10
    å¸ľ
    -0.09
    /or
    -0.09
    çļĦä¼łç»Ł
    -0.09
    ç»ĻåĪ«äºº
    -0.09
    éĥ½èĥ½å¤Ł
    -0.09
    elman
    -0.09
    åĹŁ
    -0.09
    POSITIVE LOGITS
    2
    0.11
    6
    0.11
    1
    0.11
    9
    0.11
    3
    0.10
    5
    0.10
    8
    0.10
    7
    0.10
    4
    0.10
    ÙĴ
    0.08
    Activations Density 0.390%

    No Known Activations