© 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. 117069
    Prev
    Next
    INDEX
    Explanations

    'a' followed by specific words

    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
     subject
    -0.10
    aub
    -0.09
     som
    -0.09
    igit
    -0.09
    iminal
    -0.09
     weekday
    -0.09
    aras
    -0.09
     trav
    -0.09
     familiar
    -0.08
     Classic
    -0.08
    POSITIVE LOGITS
     separate
    0.21
     seperate
    0.17
     special
    0.17
     especial
    0.15
     series
    0.14
     specially
    0.13
    special
    0.12
     Separate
    0.12
     secondary
    0.10
     specialised
    0.10
    Activations Density 0.535%

    No Known Activations