© 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. 29952
    Prev
    Next
    INDEX
    Explanations

    Kur names

    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
    nings
    -0.13
     downs
    -0.10
    eness
    -0.10
    istic
    -0.10
    frau
    -0.10
    elda
    -0.10
    occo
    -0.10
    ecs
    -0.10
    elm
    -0.10
    emouth
    -0.09
    POSITIVE LOGITS
     Cour
    0.11
     Cur
    0.11
    pios
    0.10
     cour
    0.10
    ibs
    0.10
     cred
    0.10
    ban
    0.09
    -cur
    0.09
    Cur
    0.09
     Firm
    0.09
    Activations Density 0.024%

    No Known Activations