© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9301
    Prev
    Next
    INDEX
    Explanations

    post-mortem

    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
    æİī
    -0.10
    uen
    -0.09
    åIJĪæĪIJ
    -0.09
    æ·¡åĮĸ
    -0.09
    _LVL
    -0.08
    交åıī
    -0.08
    缺åı£
    -0.08
    æ»´
    -0.08
    åĨįéĢł
    -0.08
    éľ²å¤©
    -0.08
    POSITIVE LOGITS
    æŃ»åIJİ
    0.19
    åİ»ä¸ĸ
    0.12
    éĢĿä¸ĸ
    0.12
    ÑģмеÑĢÑĤ
    0.11
    身åIJİ
    0.11
    æŃ»äºĨ
    0.10
    æ´»çĿĢ
    0.10
    å¹³æŶ
    0.10
     кваÑĢ
    0.10
    stk
    0.09
    Activations Density 0.059%

    No Known Activations