© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35246
    Prev
    Next
    INDEX
    Explanations

    datasheet documentation

    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
    车éģĵ
    -0.10
    æŶéĹ´æ®µ
    -0.10
    bars
    -0.09
    èµĸ以
    -0.09
    èģĮå·¥
    -0.09
    çŃīé¢ĨåŁŁ
    -0.09
    ibbon
    -0.09
    æıĨ
    -0.08
    (prediction
    -0.08
    æĪ¾
    -0.08
    POSITIVE LOGITS
    åŀĭåı·
    0.14
    说æĺİ书
    0.13
     specifications
    0.13
    è§Ħæł¼
    0.12
     datas
    0.12
    åİĤ家
    0.12
     Specifications
    0.12
    èµĦæĸĻ
    0.12
     specs
    0.11
     manufacturer
    0.11
    Activations Density 0.115%

    No Known Activations