© 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. 4989
    Prev
    Next
    INDEX
    Explanations

    codes/case numbers

    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
     neutral
    -0.09
     indexed
    -0.08
     numbered
    -0.08
     edited
    -0.08
     critic
    -0.08
    lete
    -0.08
     Animated
    -0.08
     animated
    -0.07
     s
    -0.07
     video
    -0.07
    POSITIVE LOGITS
    slick
    0.13
    âĢ¦↵↵↵↵
    0.12
    apat
    0.11
     {?}
    0.11
    soles
    0.11
    :');↵
    0.11
     Pais
    0.11
     moz
    0.11
     ActiveSupport
    0.11
    BOOLE
    0.10
    Activations Density 0.036%

    No Known Activations