© 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. 5673
    Prev
    Next
    INDEX
    Explanations

    genetic sequencing and mutations

    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
     respectively
    -0.09
     maternity
    -0.09
     unnamed
    -0.09
     Liber
    -0.09
     Replica
    -0.09
    ikan
    -0.09
     Mim
    -0.09
    )section
    -0.09
     anon
    -0.09
    /conf
    -0.09
    POSITIVE LOGITS
     consensus
    0.09
    fortune
    0.09
     Coming
    0.08
     meticulously
    0.08
    ayers
    0.08
     tas
    0.08
     Disabilities
    0.08
    _der
    0.08
     rough
    0.08
    coming
    0.08
    Activations Density 0.001%

    No Known Activations