© 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. 27267
    Prev
    Next
    INDEX
    Explanations

    inspires

    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
    orca
    -0.09
     thirst
    -0.09
    _pref
    -0.09
     hunts
    -0.09
     Leslie
    -0.09
    emet
    -0.09
    bull
    -0.09
     sacrifice
    -0.08
    inar
    -0.08
    pref
    -0.08
    POSITIVE LOGITS
     inspires
    0.13
     inspire
    0.12
     influence
    0.12
     elic
    0.12
     induces
    0.11
     Insp
    0.10
     coax
    0.10
     Stim
    0.10
     stimuli
    0.10
    eken
    0.10
    Activations Density 0.270%

    No Known Activations