© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9339
    Prev
    Next
    INDEX
    Explanations

    remind or taunt about celebrations

    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
    инÑĤеÑĢеÑģ
    -0.10
    åĽ½éĻħåIJĪä½ľ
    -0.10
    æ¶ī
    -0.10
    èµ°åĬ¿åĽ¾
    -0.09
    çģµæĦŁ
    -0.09
    ä¿ĿæĬ¤
    -0.09
    unks
    -0.09
    çIJĨäºĭ
    -0.08
    blank
    -0.08
     mysteries
    -0.08
    POSITIVE LOGITS
    åĺ²ç¬ij
    0.13
    çĤ«èĢĢ
    0.13
    æı¶
    0.12
     ta
    0.11
    åĺ²
    0.11
    å¾ĹæĦı
    0.11
    讥
    0.10
    ä¼ĺè¶Ĭ
    0.10
    对æ¯Ķ
    0.10
    æĮijè¡ħ
    0.10
    Activations Density 0.084%

    No Known Activations