© 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. 17269
    Prev
    Next
    INDEX
    Explanations

    immediate feedback or release

    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
    bane
    -0.11
    ç»Ī
    -0.10
    å´
    -0.10
    Incre
    -0.09
    odal
    -0.09
    eneg
    -0.09
    Intl
    -0.09
    æİĸ
    -0.09
    ä¹ħäºĨ
    -0.09
    ä¸Ģ段æŶéĹ´
    -0.09
    POSITIVE LOGITS
    马ä¸Ĭ
    0.13
    ç«ĭåĪ»
    0.12
     sofort
    0.10
     immediately
    0.10
    马ä¸Ĭå°±
    0.10
    念头
    0.10
    ç«ĭåį³
    0.10
    æĥ³åĪ°
    0.10
    è§ģæķĪ
    0.10
    æĬķåħ¥åĪ°
    0.09
    Activations Density 0.059%

    No Known Activations