© 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. 15677
    Prev
    Next
    INDEX
    Explanations

    that means

    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
     Fol
    -0.08
    ault
    -0.08
     imprint
    -0.07
     recurs
    -0.07
    obi
    -0.07
     hog
    -0.07
    kre
    -0.07
     lak
    -0.07
    etta
    -0.07
     NOT
    -0.07
    POSITIVE LOGITS
     means
    0.21
    means
    0.16
     leaves
    0.15
    Means
    0.14
     indicates
    0.14
     complic
    0.14
     Means
    0.13
     signifies
    0.13
     makes
    0.13
     mean
    0.12
    Activations Density 0.044%

    No Known Activations