© 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. 10403
    Prev
    Next
    INDEX
    Explanations

    so far

    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
    åħ·ä½ĵæĥħåĨµ
    -0.11
    æľĢçµĤ
    -0.10
    åŃĶéĽĢ
    -0.10
    åŀĭä¼ģä¸ļ
    -0.10
    ä¹ħäºĨ
    -0.10
    忽çĦ¶
    -0.09
    ä»İæѤ
    -0.09
    æľĢç»Ī
    -0.09
    èĩªæѤ
    -0.09
    ãĤĩ
    -0.09
    POSITIVE LOGITS
    geh
    0.10
    ledge
    0.09
    éĥ½æĺ¯
    0.09
    atal
    0.09
    -reaching
    0.09
    æĹłè®ºæĺ¯
    0.08
    cial
    0.08
    aven
    0.08
    /from
    0.08
    ward
    0.08
    Activations Density 0.013%

    No Known Activations