© 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. 38087
    Prev
    Next
    INDEX
    Explanations

    spreading

    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
    èļ±
    -0.10
    å¯ĨåĪĩåħ³æ³¨
    -0.10
    åŀĤ
    -0.09
    arem
    -0.09
    éĺį
    -0.09
    genesis
    -0.09
    è¿Ļè¾¹
    -0.09
    åĿij
    -0.09
    åħ¬åı¸å°Ĩ
    -0.09
    祧
    -0.09
    POSITIVE LOGITS
    å¼ĢæĿ¥
    0.16
     spreading
    0.16
     spread
    0.15
     Spread
    0.15
    Spread
    0.14
     spreads
    0.14
    spread
    0.14
    æī©æķ£
    0.14
    èĶĵ延
    0.13
    åĪĨæķ£
    0.11
    Activations Density 0.052%

    No Known Activations