© 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. 38818
    Prev
    Next
    INDEX
    Explanations

    as a

    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
    磼
    -0.10
    _DIP
    -0.09
    riba
    -0.08
    acute
    -0.08
    èĢĻ
    -0.08
    æĥ
    -0.08
    æĨ©
    -0.08
    ä½İè°ĥ
    -0.08
    çĹĩ
    -0.08
    çĶļ
    -0.08
    POSITIVE LOGITS
     недо
    0.11
    å½ĵæŶçļĦ
    0.11
    æĺİ天
    0.09
    åŁ¹åħ»åѦçĶŁ
    0.09
    Ĥæķ°
    0.09
    python
    0.09
    å½ĵæŶ
    0.08
    rush
    0.08
    æĪijå½ĵæŶ
    0.08
     ê·¸ëŀĺ
    0.08
    Activations Density 0.069%

    No Known Activations