© 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. 62619
    Prev
    Next
    INDEX
    Explanations

    new development strategies

    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
    éĢ¡
    -0.10
    ÑĪен
    -0.09
    anoia
    -0.09
    æİĸ
    -0.08
    çªŁ
    -0.08
    绿水
    -0.08
    ạt
    -0.08
    ician
    -0.08
    çĶĺ
    -0.08
    æĭ¥æĬ±
    -0.08
    POSITIVE LOGITS
    ANCES
    0.10
    èģĬ
    0.09
    nett
    0.09
    າ
    0.08
    _Word
    0.08
    å¶Ĵ
    0.08
    gMaps
    0.08
    rames
    0.08
     commun
    0.08
    æľ¬ç§ij
    0.08
    Activations Density 0.481%

    No Known Activations