© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 5948
    Prev
    Next
    INDEX
    Explanations

    female, male, sex, satisfaction

    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
     misunderstood
    -0.12
     humility
    -0.11
     Monter
    -0.10
    inth
    -0.10
     acquitted
    -0.10
     embarrassed
    -0.10
     metam
    -0.10
     redeem
    -0.10
     surrender
    -0.10
     abbreviated
    -0.10
    POSITIVE LOGITS
     satisfaction
    0.14
     Satisfaction
    0.13
    atisfaction
    0.11
     Pref
    0.11
     satisfied
    0.11
     complains
    0.10
     praises
    0.10
    Pref
    0.10
     praising
    0.10
     complimentary
    0.10
    Activations Density 0.081%

    No Known Activations