© 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. 9729
    Prev
    Next
    INDEX
    Explanations

    close relationships

    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
    äºĪ
    -0.09
    çĶŁæ¶¯
    -0.09
     Corona
    -0.08
    æ·ĭ
    -0.08
    头æĻķ
    -0.08
    è°Ĵ
    -0.07
    äºĨ好åĩł
    -0.07
    åİĨæŶ
    -0.07
    onal
    -0.07
    æ±²
    -0.07
    POSITIVE LOGITS
    çĸı
    0.11
    亲è¿ij
    0.10
    æ²®
    0.10
    æ·±åİļçļĦ
    0.10
    亲å¯Ĩ
    0.10
     bonding
    0.10
    ç¢Ĺ
    0.09
    ä¸Ģæł¹
    0.09
    纽带
    0.09
    COPE
    0.09
    Activations Density 0.042%

    No Known Activations