© 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. 112450
    Prev
    Next
    INDEX
    Explanations

    conditions, LV, system, code, power

    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
     afin
    -0.10
     partly
    -0.10
     mainly
    -0.10
     motivated
    -0.10
    coc
    -0.10
     lest
    -0.09
     fearing
    -0.09
    hon
    -0.09
     somehow
    -0.09
     pref
    -0.09
    POSITIVE LOGITS
     courtesy
    0.22
     albeit
    0.16
     Courtesy
    0.15
     via
    0.15
     thanks
    0.14
     firsthand
    0.14
     indirectly
    0.14
    via
    0.13
     unless
    0.13
    cour
    0.12
    Activations Density 0.509%

    No Known Activations