© 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. 9672
    Prev
    Next
    INDEX
    Explanations

    prices and affordability

    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
    sworth
    -0.09
    æįĤ
    -0.09
    åĮ»çĶ¨
    -0.08
    æĬ¹
    -0.08
    æ´¾
    -0.08
    å¿ħå¤ĩ
    -0.08
     mutual
    -0.08
    _chance
    -0.08
    ç½®æį¢
    -0.08
    æĹłæķ°æ¬¡
    -0.08
    POSITIVE LOGITS
     charges
    0.12
    æĶ¶è´¹æłĩåĩĨ
    0.11
    æĶ¶è´¹
    0.11
    åĥ¹
    0.10
    æĶ¶è²»
    0.10
    å¥Ĺé¤IJ
    0.10
    ä»·ä½į
    0.10
    æĬ¥ä»·
    0.10
     Rates
    0.10
    å®ļä»·
    0.09
    Activations Density 0.044%

    No Known Activations