© 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. 27442
    Prev
    Next
    INDEX
    Explanations

    what it is

    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
     Licht
    -0.09
    FROM
    -0.09
    ables
    -0.08
    ister
    -0.08
     Flam
    -0.08
     Roch
    -0.08
    aper
    -0.08
     Fleming
    -0.08
    _bases
    -0.08
    thur
    -0.08
    POSITIVE LOGITS
     that
    0.14
     streak
    0.11
    	that
    0.11
    that
    0.11
    weet
    0.10
     thats
    0.09
     about
    0.09
    >About
    0.09
     they
    0.09
     cour
    0.09
    Activations Density 0.013%

    No Known Activations