© 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. 55326
    Prev
    Next
    INDEX
    Explanations

    differ from

    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
     edi
    -0.09
    ties
    -0.09
    gesch
    -0.09
    è¿Ļ对äºİ
    -0.08
    åĵĦ
    -0.08
    åĸĩåıŃ
    -0.08
    bih
    -0.08
    owers
    -0.08
    олов
    -0.08
    ständ
    -0.08
    POSITIVE LOGITS
    rence
    0.12
    iculty
    0.11
    é¡·
    0.11
    ä¹ĭå¤Ħ
    0.10
    ingly
    0.10
    以å¾Ģ
    0.10
    å½ĵæŶçļĦ
    0.09
    etch
    0.09
    äºİ
    0.09
    ERENCE
    0.09
    Activations Density 0.018%

    No Known Activations