© 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. 5913
    Prev
    Next
    INDEX
    Explanations

    looking for specific items or services

    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
    ruk
    -0.09
     Lastly
    -0.09
     bere
    -0.08
     Aub
    -0.08
     lie
    -0.08
    Lastly
    -0.08
    orient
    -0.08
     endowed
    -0.08
    redo
    -0.08
    alf
    -0.08
    POSITIVE LOGITS
    porno
    0.11
     flap
    0.11
    pref
    0.10
    estroy
    0.10
     copp
    0.10
     culp
    0.09
    éĴ
    0.09
    lime
    0.09
     Grammar
    0.09
    warts
    0.09
    Activations Density 0.018%

    No Known Activations