© 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. 3895
    Prev
    Next
    INDEX
    Explanations

    change of

    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
    ms
    -0.10
    loo
    -0.09
    utsch
    -0.09
    rok
    -0.09
     Pont
    -0.09
    Orm
    -0.09
     ÑĥÑģп
    -0.08
     Strait
    -0.08
    yen
    -0.08
    _rates
    -0.08
    POSITIVE LOGITS
     scenery
    0.18
     pace
    0.17
     circumstance
    0.13
     circumstances
    0.13
     fortune
    0.12
     surroundings
    0.12
     seasons
    0.12
     mindset
    0.11
     venue
    0.11
     tide
    0.11
    Activations Density 0.043%

    No Known Activations