© 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. 31491
    Prev
    Next
    INDEX
    Explanations

    superhero team members

    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
    æĭ±
    -0.09
    ipsis
    -0.09
    uard
    -0.09
    äºĴèģĶäºĴéĢļ
    -0.08
    ç®Ģæĺĵ
    -0.08
    óng
    -0.08
    翼
    -0.08
    -coordinate
    -0.08
    agem
    -0.08
    isses
    -0.08
    POSITIVE LOGITS
    ä¹ĭåīįçļĦ
    0.09
    éĻį
    0.09
    éĢ¶
    0.09
    çļĦä¸ľè¥¿
    0.09
    ä¹ĭåīį
    0.08
    å¤ļå¹´çļĦ
    0.08
     CSL
    0.08
    ÑĢÑĥÑĪ
    0.08
     messenger
    0.08
     TERMIN
    0.08
    Activations Density 0.013%

    No Known Activations