© 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. 35670
    Prev
    Next
    INDEX
    Explanations

    assigned to

    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
    çĭ¬è§Ĵ
    -0.09
    å¹¼ç¨ļ
    -0.08
    ç»ħ
    -0.08
    .CLIENT
    -0.08
    çģ«èĬ±
    -0.08
    çıł
    -0.07
    å®ĩå®Ļ
    -0.07
    认
    -0.07
    人群
    -0.07
    主ä¹īèĢħ
    -0.07
    POSITIVE LOGITS
    åĨĽ
    0.17
    å®ĺåħµ
    0.16
    æľįå½¹
    0.15
    åĨĽå®ĺ
    0.15
    åĽ½å®¶å®īåħ¨
    0.15
    åĨĽäºº
    0.14
    æī§åĭ¤
    0.14
    åĨĽè®Ń
    0.13
    建åĨĽ
    0.13
    ç¾İåĨĽ
    0.13
    Activations Density 0.194%

    No Known Activations