© 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. 56788
    Prev
    Next
    INDEX
    Explanations

    comparative and 'ative' followed by study terms

    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
    á»ħn
    -0.09
    olvers
    -0.09
    ieved
    -0.09
    ê°IJ
    -0.09
    ieve
    -0.09
    æĦŁ
    -0.09
    åĽŀæĬ¥
    -0.08
    preneur
    -0.08
    åįļè§Ī
    -0.08
    åīĬ
    -0.08
    POSITIVE LOGITS
    aras
    0.09
    yas
    0.09
    åĢį
    0.08
    soon
    0.08
    ade
    0.08
    avel
    0.08
    icles
    0.08
    ptest
    0.08
    awe
    0.08
    ABEL
    0.08
    Activations Density 0.055%

    No Known Activations