© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 17219
    Prev
    Next
    INDEX
    Explanations

    look at

    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
    presence
    -0.10
     Presence
    -0.09
    åĩºç¤º
    -0.09
     irr
    -0.08
     presence
    -0.08
    충
    -0.08
    éĿ
    -0.08
    Presence
    -0.08
    proto
    -0.08
    ä¸įä»ħåı¯ä»¥
    -0.08
    POSITIVE LOGITS
    acted
    0.10
    изм
    0.09
    essed
    0.09
    è¦ģç´§
    0.09
    _SOC
    0.09
    åķ¬
    0.09
    è¿ijäºĽ
    0.09
    /stretchr
    0.09
    æĬĬè¿ĻäºĽ
    0.09
    aker
    0.08
    Activations Density 0.011%

    No Known Activations