© 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. 16414
    Prev
    Next
    INDEX
    Explanations

    make a good gift/home/statement

    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
    ause
    -0.09
     kam
    -0.09
    оÑĩ
    -0.08
     Hur
    -0.08
    acs
    -0.08
     Fell
    -0.08
     miracle
    -0.08
     fused
    -0.08
    oder
    -0.07
     Wins
    -0.07
    POSITIVE LOGITS
     excellent
    0.22
     suitable
    0.20
     ideal
    0.20
     suitability
    0.18
    ideal
    0.18
     Suitable
    0.18
     suited
    0.18
     Ideal
    0.17
    suit
    0.16
     Excellent
    0.16
    Activations Density 0.125%

    No Known Activations