© 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. 20183
    Prev
    Next
    INDEX
    Explanations

    apathetic or indifferent

    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
    èĥģ
    -0.11
    丰åİļ
    -0.10
    ä¹ĸä¹ĸ
    -0.10
    æľĽçĿĢ
    -0.10
    ä¸įæŃ¢
    -0.09
    èµŀ
    -0.09
    ç§ī
    -0.09
    éĺ»åĬĽ
    -0.09
    涩
    -0.09
    æ¶ĪåĮĸ
    -0.09
    POSITIVE LOGITS
    æ¼ł
    0.19
    çļĦæĢģ度
    0.15
    åħ³å¿ĥ
    0.15
    ä¸įåľ¨ä¹İ
    0.14
     indifference
    0.14
    åĨ·æ¼ł
    0.14
    æĢģ度
    0.13
    åħ³æ³¨åº¦
    0.13
    éĩįè§Ĩ
    0.13
    ä¸įå±ij
    0.12
    Activations Density 0.053%

    No Known Activations