© 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. 32764
    Prev
    Next
    INDEX
    Explanations

    because it

    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
     unfortunately
    -0.11
     unless
    -0.09
     preferably
    -0.09
    kö
    -0.09
     sadly
    -0.09
     hopefully
    -0.09
    unless
    -0.08
     thankfully
    -0.08
     Rage
    -0.08
    ruk
    -0.08
    POSITIVE LOGITS
     somehow
    0.17
     subconscious
    0.15
     maybe
    0.14
    ?)
    0.13
     Maybe
    0.13
     perhaps
    0.13
    ?):
    0.12
    maybe
    0.12
    ?),
    0.12
    Maybe
    0.12
    Activations Density 0.116%

    No Known Activations