© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 27437
    Prev
    Next
    INDEX
    Explanations

    describing appearance and qualities

    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
     reco
    -0.10
    oping
    -0.10
    erno
    -0.10
     Sparks
    -0.10
    enor
    -0.10
     reinc
    -0.09
     flop
    -0.09
    ailer
    -0.09
    ixon
    -0.09
     Firstly
    -0.09
    POSITIVE LOGITS
     nicely
    0.12
     belie
    0.12
     further
    0.11
     perfectly
    0.10
     making
    0.10
     brilliantly
    0.09
    -fr
    0.09
     fr
    0.09
     INTERVAL
    0.08
     fant
    0.08
    Activations Density 0.067%

    No Known Activations