© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38546
    Prev
    Next
    INDEX
    Explanations

    tips for success

    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
    hk
    -0.09
    lox
    -0.09
    è¿ĻåĿĹ
    -0.08
    æ¯ı人
    -0.08
    oley
    -0.08
    6
    -0.08
    éĬ®
    -0.08
    çľ©
    -0.08
    7
    -0.07
    梯éĺŁ
    -0.07
    POSITIVE LOGITS
    å°±èĥ½å¤Ł
    0.13
    æīįèĥ½å¤Ł
    0.12
    éĥ½èĥ½å¤Ł
    0.11
    èĥ½å¤Łè®©
    0.11
    å¯¹ä½ł
    0.10
    以åıĬåħ¶ä»ĸ
    0.10
    åħ·ä½ĵçļĦ
    0.10
    æĪĸèĢħæĺ¯
    0.10
    æ¯Ķå¦Ĥ说
    0.09
    æĺ¯æ¯Ķè¾ĥ
    0.09
    Activations Density 0.729%

    No Known Activations