© 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. 31755
    Prev
    Next
    INDEX
    Explanations

    also refer

    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
     also
    -0.11
     Hut
    -0.10
    -many
    -0.09
     Ey
    -0.09
     tat
    -0.08
    mart
    -0.08
    <|fim_suffix|>
    -0.08
    ä¹Ł
    -0.08
    UT
    -0.08
    ICS
    -0.08
    POSITIVE LOGITS
    usk
    0.10
     Interested
    0.10
    disp
    0.10
     Alto
    0.10
    esis
    0.10
    osten
    0.10
     interested
    0.09
     stumble
    0.09
    RELATED
    0.09
     nett
    0.09
    Activations Density 0.029%

    No Known Activations