© 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. 111362
    Prev
    Next
    INDEX
    Explanations

    from afar

    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
    Negative Logits
    Æ°á»
    -0.12
     hitch
    -0.11
    _manual
    -0.11
    ulle
    -0.11
    owie
    -0.10
     Owens
    -0.10
    vest
    -0.10
    antic
    -0.10
    å»
    -0.10
    alic
    -0.10
    POSITIVE LOGITS
     afar
    0.45
     distance
    0.44
     distant
    0.41
     Distance
    0.39
    distance
    0.35
    Distance
    0.34
     distances
    0.32
    -distance
    0.31
     remotely
    0.27
    _distance
    0.26
    Activations Density 0.191%

    No Known Activations