© 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. 25488
    Prev
    Next
    INDEX
    Explanations

    get or got to the

    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
     Coron
    -0.08
    elen
    -0.08
    jen
    -0.08
     Moor
    -0.08
     Daily
    -0.07
    _loc
    -0.07
    kus
    -0.07
    egen
    -0.07
    orny
    -0.07
    Toggle
    -0.07
    POSITIVE LOGITS
     clue
    0.26
     cue
    0.25
     hint
    0.24
     Hint
    0.21
     cues
    0.21
     clues
    0.19
     hints
    0.19
     heed
    0.18
     realise
    0.17
    Hint
    0.17
    Activations Density 0.064%

    No Known Activations