© 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. 48677
    Prev
    Next
    INDEX
    Explanations

    introduces contrast

    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
     truth
    -0.09
     frankly
    -0.09
    ASN
    -0.08
     ðŁĺī
    -0.08
    avian
    -0.08
     suspect
    -0.08
     stil
    -0.08
     honestly
    -0.08
     Lancaster
    -0.08
     ALSO
    -0.08
    POSITIVE LOGITS
     Trot
    0.12
     awaits
    0.11
    zin
    0.11
     deferred
    0.10
    ÑģÑĤÑĢ
    0.10
    è½
    0.10
    âĢ¦âĢ¦↵↵
    0.10
     reportedly
    0.10
    apiro
    0.10
    orre
    0.10
    Activations Density 0.787%

    No Known Activations