© 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. 19443
    Prev
    Next
    INDEX
    Explanations

    category by, | oil, ( find

    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
    两ä¸ī
    -0.08
     Solomon
    -0.08
    holder
    -0.08
    çĭ¬
    -0.08
    imenti
    -0.08
    å°±æĺ¯åľ¨
    -0.08
    obb
    -0.08
    èĥĮåIJİ
    -0.08
    以éĺ²
    -0.07
    èĬ¦
    -0.07
    POSITIVE LOGITS
    è¯Ŀé¢ĺ
    0.11
    çļĦè¯Ŀé¢ĺ
    0.10
    è¿ĻåĿĹ
    0.10
    èĮĥçķ´
    0.09
    麼
    0.09
    å·²ç»ıè¶ħè¿ĩ
    0.09
    çº
    0.09
    _fatal
    0.09
     topics
    0.09
    usu
    0.09
    Activations Density 0.248%

    No Known Activations