© 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. 26110
    Prev
    Next
    INDEX
    Explanations

    substant and substantial

    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
    ging
    -0.11
    tures
    -0.11
    ged
    -0.10
    ges
    -0.09
    antine
    -0.09
    patch
    -0.09
     sorry
    -0.09
    ature
    -0.09
    cks
    -0.09
    uce
    -0.08
    POSITIVE LOGITS
    ively
    0.13
    лÑİ
    0.11
     Abuse
    0.11
    iveness
    0.10
    anon
    0.10
     abuse
    0.10
    jal
    0.10
    hower
    0.10
    лÑı
    0.09
    fov
    0.09
    Activations Density 0.052%

    No Known Activations