© 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. 17170
    Prev
    Next
    INDEX
    Explanations

    pulled with it, placing it at her cunt’s entrance. When Bill plunged into the very

    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
     creep
    -0.09
    oni
    -0.09
     Sac
    -0.08
    ripple
    -0.08
     responder
    -0.08
    irs
    -0.08
     shear
    -0.08
    Sac
    -0.08
    Responder
    -0.07
     Kann
    -0.07
    POSITIVE LOGITS
     bewild
    0.11
    ugo
    0.11
     improvised
    0.11
     weakened
    0.10
    mund
    0.10
     Crow
    0.10
     equivalents
    0.10
     slack
    0.10
     stunned
    0.10
     cot
    0.10
    Activations Density 0.013%

    No Known Activations