© 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. 30633
    Prev
    Next
    INDEX
    Explanations

    from Russia or mkerrors

    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
     neither
    -0.09
    <|fim_suffix|>
    -0.09
     threaten
    -0.08
     unnecessarily
    -0.08
     surve
    -0.08
     hairy
    -0.08
     approximately
    -0.08
     almost
    -0.08
     unsuccessfully
    -0.08
     peel
    -0.08
    POSITIVE LOGITS
     accordingly
    0.12
     reckon
    0.10
     assorted
    0.10
    asel
    0.10
     Quarry
    0.10
     splendid
    0.09
     worthwhile
    0.09
    aspect
    0.09
    ansi
    0.09
    âħ
    0.09
    Activations Density 0.074%

    No Known Activations