© 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. 59029
    Prev
    Next
    INDEX
    Explanations

    Titan and Texans

    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
    å°ijäºĨ
    -0.09
    ammers
    -0.09
    æģ¬
    -0.09
    åİŁåĽłä¹ĭä¸Ģ
    -0.09
    æ²»
    -0.09
     DeV
    -0.09
    åĮ¡
    -0.09
    CriticalSection
    -0.09
    teenth
    -0.08
    hti
    -0.08
    POSITIVE LOGITS
    inos
    0.10
    uary
    0.09
    ozo
    0.09
    hosts
    0.09
    ONLY
    0.09
    ments
    0.08
     CCTV
    0.08
    ä¸Ľä¹¦
    0.08
    ings
    0.08
    heit
    0.08
    Activations Density 0.002%

    No Known Activations