© 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. 3939
    Prev
    Next
    INDEX
    Explanations

    acceptable, desirable, worthwhile

    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
    inth
    -0.11
     Bren
    -0.11
    ecc
    -0.10
    observer
    -0.10
     Schul
    -0.10
    iswa
    -0.10
     Lazy
    -0.10
     Stanton
    -0.10
    hes
    -0.10
    ween
    -0.10
    POSITIVE LOGITS
     acceptable
    0.18
     worthwhile
    0.17
     worth
    0.16
     desirable
    0.15
    acceptable
    0.13
     worthy
    0.12
     preferable
    0.12
     viable
    0.12
     Worth
    0.12
     suitable
    0.12
    Activations Density 0.064%

    No Known Activations