© 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. 61069
    Prev
    Next
    INDEX
    Explanations

    refactor, actor, actoring

    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
    æīŃ转
    -0.11
    ï¸
    -0.10
    ny
    -0.09
    quil
    -0.09
    ä¸ĢåŃĹ
    -0.09
    NY
    -0.08
    ç»Ī究
    -0.08
    éĹ
    -0.08
    -language
    -0.08
    Sp
    -0.08
    POSITIVE LOGITS
    stadt
    0.11
    带走
    0.10
    æĬ¤
    0.10
    èŃ·
    0.10
    èħ®
    0.10
    å¡ijéĢł
    0.09
    æ¸IJ
    0.09
    æİ£
    0.09
    akistan
    0.08
    каÑĢ
    0.08
    Activations Density 0.050%

    No Known Activations