© 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. 48475
    Prev
    Next
    INDEX
    Explanations

    soft, gentle, cushion

    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
    arel
    -0.12
    busy
    -0.11
     proportions
    -0.11
     thirsty
    -0.10
    enser
    -0.10
    Them
    -0.10
    lek
    -0.10
    RAP
    -0.10
    usto
    -0.10
    /calendar
    -0.10
    POSITIVE LOGITS
     gentle
    0.14
    -hard
    0.14
     landing
    0.13
     gent
    0.13
     gently
    0.13
     Hard
    0.12
     tender
    0.12
     blow
    0.11
     cushion
    0.11
     hard
    0.11
    Activations Density 0.072%

    No Known Activations