© 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. 62781
    Prev
    Next
    INDEX
    Explanations

    seeking companionship or dates

    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
    ç«ĭæ¡Ī
    -0.09
    æĺ¯æĪijåĽ½
    -0.09
     Polar
    -0.08
     polar
    -0.08
    éĻ·
    -0.07
    åĴ³åĹ½
    -0.07
    BAR
    -0.07
     deluxe
    -0.07
    9
    -0.07
    2
    -0.07
    POSITIVE LOGITS
    ä¼´ä¾£
    0.11
    æ°¸ä¹ħ
    0.11
     companions
    0.10
    æµ£
    0.10
    æIJŃæ¡£
    0.10
    appable
    0.10
    强èĢħ
    0.10
    æĻ¤
    0.10
     accompany
    0.10
     accompanies
    0.10
    Activations Density 0.062%

    No Known Activations