© 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. 27309
    Prev
    Next
    INDEX
    Explanations

    gambling, casinos, slots, poker, betting

    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
    庸
    -0.10
    æĮ¤
    -0.09
    ÑIJ
    -0.09
    樱
    -0.09
    çĮľæµĭ
    -0.09
    æ¦Ħ
    -0.09
    æ¡ī
    -0.09
    çĮľ
    -0.09
    ombre
    -0.09
    è¿ĺéľĢ
    -0.09
    POSITIVE LOGITS
    åIJį人
    0.10
    åĪ®
    0.09
    æī«çłģ
    0.09
    _sa
    0.08
    éħ¬
    0.08
     ÑģÑĥ
    0.08
    hte
    0.08
    PTY
    0.08
    é£İ鼨
    0.08
    产ä¸ļåĽŃ
    0.08
    Activations Density 0.072%

    No Known Activations