© 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. 112487
    Prev
    Next
    INDEX
    Explanations

    Comp, compound, compelling

    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
    ities
    -0.10
    (es
    -0.09
    igo
    -0.09
    azo
    -0.09
     mell
    -0.08
    cbc
    -0.08
     Simone
    -0.08
    acle
    -0.08
     Misc
    -0.08
     gord
    -0.08
    POSITIVE LOGITS
    licated
    0.15
    ÑĮÑİ
    0.13
    artment
    0.13
    licity
    0.13
    urar
    0.12
    ulsive
    0.12
    lications
    0.12
    ounding
    0.11
    ulated
    0.11
    aign
    0.10
    Activations Density 0.110%

    No Known Activations