© 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. 4842
    Prev
    Next
    INDEX
    Explanations

    license or version specifications

    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
     ;)↵↵
    -0.11
     ha
    -0.11
     FA
    -0.11
     ðŁĺī
    -0.10
     haar
    -0.10
     dusty
    -0.09
     litt
    -0.09
     :)↵↵
    -0.09
    lier
    -0.09
     pretty
    -0.09
    POSITIVE LOGITS
    ruk
    0.09
     tremend
    0.09
     Daw
    0.09
     Corm
    0.08
    berger
    0.08
     fel
    0.08
     trg
    0.08
     internally
    0.08
     Abed
    0.08
    ICY
    0.08
    Activations Density 0.016%

    No Known Activations