© 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. 36028
    Prev
    Next
    INDEX
    Explanations

    problems with

    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
    éĿĴèĽĻ
    -0.09
    ä¸įåIJĮç¨ĭ度
    -0.08
    纳æĸ¯
    -0.08
    容
    -0.08
    åĴĨ
    -0.08
    çĶŁæķĪ
    -0.08
    åĿIJ
    -0.07
    åħ¨æĸĩ
    -0.07
    argin
    -0.07
    æµĭè¯Ħ
    -0.07
    POSITIVE LOGITS
    麻çĥ¦
    0.15
    ä¸Ģ个éĹ®é¢ĺ
    0.11
    leh
    0.10
    arb
    0.10
    IMER
    0.10
    èĨº
    0.10
    串
    0.09
    rene
    0.09
    atic
    0.09
    丼
    0.09
    Activations Density 0.095%

    No Known Activations