© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 115436
    Prev
    Next
    INDEX
    Explanations

    when

    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
     when
    -0.13
     When
    -0.11
     WHEN
    -0.10
    When
    -0.10
     furthermore
    -0.09
     Rum
    -0.09
    _when
    -0.09
    udes
    -0.09
    TEL
    -0.09
     div
    -0.09
    POSITIVE LOGITS
    ering
    0.10
    -ever
    0.09
    perm
    0.08
     necessary
    0.08
    ellen
    0.08
     Eid
    0.08
     sober
    0.08
     dizzy
    0.08
    uta
    0.08
     whim
    0.08
    Activations Density 0.115%

    No Known Activations