© 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. 34022
    Prev
    Next
    INDEX
    Explanations

    erotic or Erik

    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
    æĤłæĤł
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    aged
    -0.08
    Prot
    -0.08
    isser
    -0.08
    ause
    -0.08
    ael
    -0.08
    åıijåĬ¨
    -0.08
    yii
    -0.08
    åĥļ
    -0.08
    POSITIVE LOGITS
    ting
    0.12
    DBObject
    0.10
    etes
    0.09
    åĥ¦
    0.09
    æĢ§å¼º
    0.09
    ä½ļ
    0.09
    обÑħодим
    0.09
    æĦ«
    0.09
    иÑĤеÑĤ
    0.09
    akis
    0.09
    Activations Density 0.003%

    No Known Activations