© 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. 34134
    Prev
    Next
    INDEX
    Explanations

    autumn season, autumn moon, autumn again

    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
    ied
    -0.10
    erge
    -0.09
    ç¬Ħ
    -0.09
    ges
    -0.09
    éĺĤ
    -0.09
    gable
    -0.08
    çIJIJ
    -0.08
    å¼łæī¬
    -0.08
    adin
    -0.08
    æ´½
    -0.08
    POSITIVE LOGITS
    elves
    0.12
    izer
    0.11
    ality
    0.10
     dolayı
    0.10
    ed
    0.10
    ize
    0.09
    nier
    0.09
    izing
    0.09
    entication
    0.09
    ized
    0.09
    Activations Density 0.003%

    No Known Activations