© 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. 6974
    Prev
    Next
    INDEX
    Explanations

    changes in biological levels

    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
    entic
    -0.13
    tele
    -0.12
     Haram
    -0.11
    sip
    -0.11
    igi
    -0.11
     Commons
    -0.11
     bab
    -0.11
    ngle
    -0.11
    ocs
    -0.11
    aten
    -0.11
    POSITIVE LOGITS
     your
    0.12
     blood
    0.11
     their
    0.08
     Your
    0.08
     YOUR
    0.08
    your
    0.08
     libido
    0.08
     Circus
    0.07
    idth
    0.07
     levels
    0.07
    Activations Density 0.016%

    No Known Activations