© 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. 4650
    Prev
    Next
    INDEX
    Explanations

    without followed by a verb

    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
    sek
    -0.09
     Entrance
    -0.09
    —for
    -0.09
     Bravo
    -0.09
     entry
    -0.09
    okus
    -0.09
     excl
    -0.08
     ENTRY
    -0.08
     entrance
    -0.08
    ival
    -0.08
    POSITIVE LOGITS
    allen
    0.10
    onga
    0.10
     narc
    0.09
     plac
    0.09
     flick
    0.09
    yne
    0.09
    ĥģ
    0.09
    cut
    0.09
    reh
    0.08
     pans
    0.08
    Activations Density 0.003%

    No Known Activations