© 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. 30065
    Prev
    Next
    INDEX
    Explanations

    online dating sites

    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
    æĬĺåıł
    -0.11
    _here
    -0.09
    лав
    -0.09
    çĨı
    -0.08
    æ¶īæ¡Ī
    -0.08
    Enum
    -0.08
    åĪĿäºĮ
    -0.08
    èĪ¶
    -0.08
     Kültür
    -0.08
    åŀĭåı·
    -0.08
    POSITIVE LOGITS
    å¹³åı°ä¸Ĭ
    0.09
    ä¸Ĭæľī
    0.09
    ancia
    0.09
    è§Ĥ
    0.08
    溲
    0.08
    ãĤµãĤ¤ãĥĪ
    0.08
    orta
    0.08
    orca
    0.08
    åĻ¨å®ĺ
    0.08
    _TRACE
    0.08
    Activations Density 0.025%

    No Known Activations