© 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. 115942
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Č
    -0.13
    IFn
    -0.13
    Disappear
    -0.12
    Č↵
    -0.12
     Unidos
    -0.11
    _reordered
    -0.11
     _$
    -0.10
     covid
    -0.10
    Slf
    -0.10
    \Dependency
    -0.10
    POSITIVE LOGITS
    :.
    0.10
     reportedly
    0.10
    ".↵↵
    0.09
    <|endoftext|>
    0.09
    ÐĴ
    0.08
    0.08
    .".
    0.08
     anime
    0.08
    imi
    0.08
    featured
    0.08
    Activations Density 0.025%

    No Known Activations