© 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. 17343
    Prev
    Next
    INDEX
    Explanations

    `without` warranty

    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
    ahi
    -0.08
    ayan
    -0.08
     charges
    -0.08
    aine
    -0.08
     repr
    -0.08
     reel
    -0.08
    rete
    -0.07
    315
    -0.07
    302
    -0.07
     retaliation
    -0.07
    POSITIVE LOGITS
    oga
    0.12
     Wants
    0.12
     Isa
    0.11
    æŃ£åľ¨
    0.11
    aybe
    0.10
     desires
    0.10
    illes
    0.10
     wants
    0.10
     Vert
    0.10
     Sick
    0.10
    Activations Density 0.002%

    No Known Activations