© 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. 48951
    Prev
    Next
    INDEX
    Explanations

    by way of / by name

    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®ķ
    -0.09
    ä¹ĭå¤ľ
    -0.09
    ãĤ¢ãĥ³
    -0.09
    ä¹ĭä½Ļ
    -0.09
    ually
    -0.09
    immers
    -0.09
    çĻĤ
    -0.09
    enz
    -0.09
    ensively
    -0.09
    ennie
    -0.09
    POSITIVE LOGITS
    éĻª
    0.10
    èµ´
    0.10
     Ske
    0.08
    妹
    0.08
    éĺ²ç©º
    0.08
    å½Ŀ
    0.08
     stri
    0.07
    ä¿®
    0.07
    çĶļä¹Ī
    0.07
    èĮħ
    0.07
    Activations Density 0.005%

    No Known Activations