© 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. 61767
    Prev
    Next
    INDEX
    Explanations

    for its

    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
    åĩij
    -0.09
    æīĵçĮİ
    -0.09
    ç¿ĺ
    -0.09
    éĿĻéĿĻåľ°
    -0.08
    æ²ŁéĢļ
    -0.08
     пÑĢеимÑĥÑīеÑģÑĤв
    -0.08
     lei
    -0.08
     EINVAL
    -0.08
    atz
    -0.08
    顺
    -0.08
    POSITIVE LOGITS
    åħ¶æīĢ
    0.09
    éĤ£å¤©
    0.09
    å½»åºķ
    0.09
    顽
    0.09
    æĶ¾æīĭ
    0.09
     fract
    0.08
    çIJ¦
    0.08
    å´İ
    0.08
    igs
    0.08
    æĮijåīĶ
    0.08
    Activations Density 0.044%

    No Known Activations