© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 20573
    Prev
    Next
    INDEX
    Explanations

    call to action

    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
    sWith
    -0.10
    OLER
    -0.09
    ntag
    -0.09
    è°ľ
    -0.09
    æŁIJç§į
    -0.08
    æ¯ĽåŃĶ
    -0.08
    vens
    -0.08
     Ä°l
    -0.08
    éĻ¶
    -0.08
    inas
    -0.08
    POSITIVE LOGITS
    åĴĮå°ļ
    0.11
    NESS
    0.11
    æĽ·
    0.10
    bek
    0.09
    LAG
    0.09
    -Cs
    0.09
    æ¯Ĥ
    0.09
    åįģ大
    0.09
    人éĢī
    0.09
    Pressed
    0.09
    Activations Density 0.156%

    No Known Activations