© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59095
    Prev
    Next
    INDEX
    Explanations

    multi- prefix detection

    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
    æ»ĵ
    -0.09
    oir
    -0.08
    idd
    -0.08
     slur
    -0.08
    alous
    -0.08
    ophobic
    -0.08
    ajan
    -0.08
    åħĨ
    -0.07
    åīįæıIJæĺ¯
    -0.07
    gett
    -0.07
    POSITIVE LOGITS
    plier
    0.17
     sclerosis
    0.16
    plied
    0.14
    pliers
    0.13
    IPLE
    0.13
    -purpose
    0.12
    PLIER
    0.12
    å¤ļæł·
    0.11
    iple
    0.11
    麼
    0.11
    Activations Density 0.145%

    No Known Activations