© 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. 38144
    Prev
    Next
    INDEX
    Explanations

    spider species

    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
    ä¹Łå¥½
    -0.10
    解èĦ±
    -0.09
    éħį
    -0.09
    _DIP
    -0.08
    èĤī
    -0.08
    èĤīç±»
    -0.08
    IBE
    -0.08
    chron
    -0.08
    çļĦç»ıåİĨ
    -0.08
     rab
    -0.08
    POSITIVE LOGITS
    èľĺèĽĽ
    0.13
     spiders
    0.10
     spider
    0.09
    ç»ĩ
    0.09
    rollo
    0.09
     SMART
    0.09
    æķ²
    0.09
    访
    0.09
    èĽĽ
    0.09
     пÑĢеимÑĥÑīеÑģÑĤв
    0.08
    Activations Density 0.118%

    No Known Activations