© 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. 18702
    Prev
    Next
    INDEX
    Explanations

    original

    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
    poke
    -0.09
    åİ¥
    -0.09
    æģĤ
    -0.09
    sel
    -0.09
    åĵ¨
    -0.08
    åģ¶çĦ¶
    -0.08
    é¾Ħ
    -0.08
    æĪĸå¤ļ
    -0.08
     беÑģплаÑĤно
    -0.08
    onen
    -0.08
    POSITIVE LOGITS
    ity
    0.13
    æĢ§å¼º
    0.11
    ITY
    0.10
    udge
    0.10
    æŃ£çīĪ
    0.09
    iginal
    0.09
    UDGE
    0.09
    èįĥ
    0.09
    åĩºè®©
    0.09
    ople
    0.09
    Activations Density 0.023%

    No Known Activations