© 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. 51968
    Prev
    Next
    INDEX
    Explanations

    warranties and warnings

    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
    portun
    -0.11
    èIJ¥
    -0.11
    æŁ±
    -0.09
    kul
    -0.09
    ulle
    -0.09
    æŀ¶æŀĦ
    -0.08
    Pet
    -0.08
    亦
    -0.08
    åı¯ä»¥çĶ¨
    -0.08
    pet
    -0.08
    POSITIVE LOGITS
    èѦåijĬ
    0.14
    èŃ¦ç¤º
    0.11
     warnings
    0.10
    误导
    0.10
     warning
    0.10
    强åĪ¶
    0.10
     Warn
    0.09
    -warning
    0.09
     WARRANTY
    0.09
    ä¿¡æģ¯æľįåĬ¡
    0.09
    Activations Density 0.170%

    No Known Activations