© 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. 9999
    Prev
    Next
    INDEX
    Explanations

    as long as

    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
     zwar
    -0.10
    ä¹ĭæīĢ以
    -0.09
    urn
    -0.09
    èĻ½çĦ¶
    -0.09
    åı£åı·
    -0.09
    éĿŀ常éĢĤåIJĪ
    -0.09
    èĻ½
    -0.08
    ideal
    -0.08
    æĢİä¹Īåı¯èĥ½
    -0.08
    åıªèĥ½è¯´
    -0.08
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.12
    è¶³å¤Ł
    0.11
    æľīè¶³å¤ŁçļĦ
    0.10
    å²Ķ
    0.10
    ä¸įèĩ³äºİ
    0.10
     Äijừng
    0.10
    å®Īä½ı
    0.10
    èĥ½å¾ĹåĪ°
    0.09
    å¤Ł
    0.09
    æľī个
    0.09
    Activations Density 0.062%

    No Known Activations