© 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. 34457
    Prev
    Next
    INDEX
    Explanations

    namespace

    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
    allen
    -0.09
    ement
    -0.09
    çİĭåĽ½
    -0.09
    èĵĿ天
    -0.08
    ä¸ĢéĶ®
    -0.08
    cial
    -0.08
    æīĥ
    -0.08
    éĻĪè¿°
    -0.08
    ture
    -0.08
    åºĬä¸Ĭ
    -0.08
    POSITIVE LOGITS
    èı±
    0.10
    åŁºæķ°
    0.09
    æ£
    0.09
     Disp
    0.09
    é»İæĺİ
    0.08
    åĪĩ
    0.08
    pon
    0.08
     currency
    0.08
    棱
    0.08
     dispens
    0.08
    Activations Density 0.059%

    No Known Activations