© 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. 15960
    Prev
    Next
    INDEX
    Explanations

    file attachments or data links

    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
     DVDs
    -0.12
     tapes
    -0.11
    agger
    -0.09
    ?page
    -0.09
    loe
    -0.09
    ÑĥÑĢ
    -0.09
    imity
    -0.09
    .Clone
    -0.09
     illustrations
    -0.09
     fulfilling
    -0.09
    POSITIVE LOGITS
     Attachment
    0.15
     attachment
    0.15
    Attachment
    0.13
     bytes
    0.13
     KB
    0.12
    âĢİ
    0.12
     attachments
    0.12
    attachment
    0.12
    Spoiler
    0.11
    Bytes
    0.11
    Activations Density 0.262%

    No Known Activations