© 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. 39295
    Prev
    Next
    INDEX
    Explanations

    that followed by 'I' or 'is'

    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
    å¾Ĺä¸įåĪ°
    -0.10
    éĩĿ
    -0.10
    éĴĪ
    -0.10
    è¾¾ä¸įåĪ°
    -0.09
    udit
    -0.09
    upon
    -0.09
    æ¿Ĵ
    -0.09
    çģ¿çĥĤ
    -0.09
    èģĴ
    -0.09
    çļĦ缮æłĩ
    -0.08
    POSITIVE LOGITS
     where
    0.12
    where
    0.10
     où
    0.09
    awan
    0.09
     Disclosure
    0.09
    tern
    0.08
    ìĹIJìĦľëĬĶ
    0.08
    unch
    0.08
     Rip
    0.08
     где
    0.08
    Activations Density 0.253%

    No Known Activations