© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 92298
    Prev
    Next
    INDEX
    Explanations

    this followed by punctuation or verb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    bcywinski/Olmo-3-32B-Base-SAE/saes_allenai_Olmo-3-1125-32B_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
    è¿Ļ
    -0.14
     this
    -0.12
     THIS
    -0.12
    this
    -0.12
     these
    -0.11
    	this
    -0.11
     nÃły
    -0.11
     estas
    -0.11
    these
    -0.11
     THESE
    -0.10
    POSITIVE LOGITS
    osi
    0.12
     Bun
    0.11
    éĤ
    0.10
    anst
    0.10
    fen
    0.10
    _vect
    0.10
     Cabin
    0.10
    BUM
    0.10
     That
    0.09
    ãģĿãģ®
    0.09
    Activations Density 0.232%

    No Known Activations