© 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. 4775
    Prev
    Next
    INDEX
    Explanations

    shame, sad, unfortunate

    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
    æIJĶ
    -0.11
    ssi
    -0.09
    è¿Ļ座åŁİå¸Ĥ
    -0.09
     nowhere
    -0.08
    ETCH
    -0.08
    æľĢåĸľæ¬¢
    -0.08
    2
    -0.08
    ivity
    -0.08
    ç¥ŀåĻ¨
    -0.08
    3
    -0.08
    POSITIVE LOGITS
    声èªī
    0.10
    fully
    0.10
    eus
    0.09
    -hearted
    0.09
    oldt
    0.09
    iard
    0.09
    çĹħæ¯ĴæĦŁæŁĵ
    0.09
    canf
    0.09
    childs
    0.09
    tre
    0.08
    Activations Density 0.004%

    No Known Activations