© 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. 55581
    Prev
    Next
    INDEX
    Explanations

    rigid

    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
    å¸ļ
    -0.10
    quam
    -0.10
    å¾ij
    -0.09
    éĻIJãĤĬ
    -0.09
    strand
    -0.08
    anzi
    -0.08
    ing
    -0.08
    eshire
    -0.08
     обÑĢазованиÑı
    -0.08
    ложен
    -0.08
    POSITIVE LOGITS
    mente
    0.11
    -wing
    0.10
    -ish
    0.10
    ement
    0.09
    åľ°è¯´
    0.09
     ìŀIJ리
    0.09
    imize
    0.09
    imizer
    0.09
    ITY
    0.09
    ities
    0.08
    Activations Density 0.030%

    No Known Activations