© 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. 26695
    Prev
    Next
    INDEX
    Explanations

    M followed by various characters

    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
    eter
    -0.12
    oves
    -0.11
    oved
    -0.11
    oney
    -0.10
    ovies
    -0.10
     Kes
    -0.10
    utations
    -0.10
    oran
    -0.10
    onta
    -0.10
     Perkins
    -0.10
    POSITIVE LOGITS
    hm
    0.14
     hm
    0.13
     hmm
    0.13
    mmm
    0.13
    mm
    0.13
     Hmm
    0.12
    Hmm
    0.11
    m
    0.11
    oga
    0.10
    oped
    0.10
    Activations Density 0.037%

    No Known Activations