© 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. 31388
    Prev
    Next
    INDEX
    Explanations

    Enter your email

    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
     /*----------------------------------------------------------------
    -0.10
    ael
    -0.10
    roy
    -0.10
    ripper
    -0.10
     bite
    -0.10
    fel
    -0.10
     Kong
    -0.10
    tics
    -0.09
     Willis
    -0.09
    Resolver
    -0.09
    POSITIVE LOGITS
     here
    0.09
     departure
    0.09
    éĤ®ç®±
    0.09
     Pool
    0.09
    cast
    0.08
    @update
    0.08
     crib
    0.08
    IData
    0.08
    EmailAddress
    0.08
     departing
    0.08
    Activations Density 0.001%

    No Known Activations