© 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. 15317
    Prev
    Next
    INDEX
    Explanations

    looks like, here appears

    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
    hint
    -0.10
     gab
    -0.10
     pacing
    -0.09
     watchers
    -0.09
    felt
    -0.09
     freed
    -0.09
     felt
    -0.09
     intoler
    -0.09
    ай
    -0.09
    raq
    -0.09
    POSITIVE LOGITS
     here
    0.17
     seems
    0.16
    Looks
    0.15
     Looks
    0.15
     looks
    0.14
    looks
    0.14
     appears
    0.14
     Seems
    0.13
    here
    0.13
     evidently
    0.13
    Activations Density 0.049%

    No Known Activations