© 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. 7295
    Prev
    Next
    INDEX
    Explanations

    Linux Systems

    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
    ä½İè°ĥ
    -0.08
    avy
    -0.08
     ink
    -0.08
    éŨ
    -0.08
    ãĤŃãĥ³ãĤ°
    -0.07
     Zend
    -0.07
    ocol
    -0.07
     Hank
    -0.07
    ãģĽãģĦ
    -0.07
     unc
    -0.07
    POSITIVE LOGITS
    éĤĵå°ıå¹³
    0.12
    IDADE
    0.10
    æĸ°ä¸ŃåĽ½
    0.10
     поб
    0.10
    Ñīи
    0.10
    åĩºåĶ®
    0.09
     classics
    0.09
     Antar
    0.09
    classic
    0.09
    éĢĢå½¹åĨĽäºº
    0.09
    Activations Density 0.580%

    No Known Activations