© 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. 26823
    Prev
    Next
    INDEX
    Explanations

    saving you effort or starting assistance

    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
     desper
    -0.10
    datable
    -0.10
    ams
    -0.09
    KC
    -0.09
    ç´
    -0.09
     \"$
    -0.09
    иÑĩ
    -0.09
    ä¼
    -0.09
    ousel
    -0.09
     Kens
    -0.09
    POSITIVE LOGITS
     conveniently
    0.15
     convenience
    0.14
     already
    0.13
     ahead
    0.12
     done
    0.12
     Done
    0.12
     starter
    0.11
     ease
    0.11
     eased
    0.11
     Helpful
    0.11
    Activations Density 0.143%

    No Known Activations