© 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. 111951
    Prev
    Next
    INDEX
    Explanations

    introductions and clauses

    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
     Circ
    -0.08
     armed
    -0.07
     Bellev
    -0.07
    advance
    -0.07
     near
    -0.07
     denial
    -0.07
     adm
    -0.07
     circum
    -0.06
     hum
    -0.06
    ynom
    -0.06
    POSITIVE LOGITS
     fact
    0.22
     contrast
    0.16
    fact
    0.15
     truth
    0.15
     fairness
    0.15
     addition
    0.13
    ev
    0.12
    cred
    0.12
     itself
    0.12
    justice
    0.12
    Activations Density 0.121%

    No Known Activations