© 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. 17419
    Prev
    Next
    INDEX
    Explanations

    URLs and programming code

    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
     clutch
    -0.10
     DETAILS
    -0.10
     dame
    -0.09
     Mistress
    -0.09
     accompagn
    -0.09
    iry
    -0.09
    bbox
    -0.09
    agrams
    -0.09
    /classes
    -0.09
     granted
    -0.09
    POSITIVE LOGITS
     Clayton
    0.09
     Greenwood
    0.09
    ime
    0.09
    igan
    0.09
    illo
    0.08
     fe
    0.08
     drafts
    0.08
    icare
    0.08
    UBE
    0.08
    ube
    0.08
    Activations Density 0.001%

    No Known Activations