© 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. 25898
    Prev
    Next
    INDEX
    Explanations

    numbers after 'in' or '('

    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
    ÑĨ
    -0.09
    inals
    -0.09
    -worthy
    -0.09
     foyer
    -0.08
     verte
    -0.08
    anine
    -0.08
    anos
    -0.08
     Adj
    -0.08
    adj
    -0.08
     Province
    -0.08
    POSITIVE LOGITS
     similarly
    0.18
     ebenfalls
    0.17
     similar
    0.15
     likewise
    0.13
    similar
    0.12
     much
    0.11
     Similar
    0.11
    Similar
    0.10
     MUCH
    0.10
     equally
    0.10
    Activations Density 0.040%

    No Known Activations