© 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. 53097
    Prev
    Next
    INDEX
    Explanations

    thoughtful and considerate actions

    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
    æ³¥åľŁ
    -0.09
    çĽı
    -0.09
    æ¼Ĥ
    -0.09
    彩
    -0.09
     Burb
    -0.09
    licht
    -0.08
    è°Ī
    -0.08
    åĶ¾
    -0.08
    ëŀĮ
    -0.08
    onymous
    -0.08
    POSITIVE LOGITS
    身边çļĦ
    0.11
    룸
    0.11
    人éĢł
    0.10
    è°£
    0.09
    åĩºèµĦ
    0.09
    çļĦæķ´ä½ĵ
    0.09
     Ston
    0.09
    CADE
    0.09
    çļĦå®ŀéĻħ
    0.09
    ä½ĵè´´
    0.09
    Activations Density 0.010%

    No Known Activations