© 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. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 49172
    Prev
    Next
    INDEX
    Explanations

    still + negation or continuation

    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
     Fleming
    -0.14
    æļ
    -0.13
     amort
    -0.12
    porter
    -0.11
    alls
    -0.11
     Isl
    -0.11
    .Formatter
    -0.11
     momentarily
    -0.11
    "type
    -0.11
    Votes
    -0.11
    POSITIVE LOGITS
     haven
    0.15
     hasn
    0.15
     hadn
    0.14
     persist
    0.12
    æľª
    0.11
     unresolved
    0.11
    haven
    0.11
     alive
    0.11
     unfinished
    0.11
    没æľī
    0.11
    Activations Density 0.114%

    No Known Activations