© 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. 31238
    Prev
    Next
    INDEX
    Explanations

    Rattler, Ratcliffe, Ratner, ratfish, ratifying, Rathore

    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
    ries
    -0.10
    erson
    -0.09
    iro
    -0.09
     Tyson
    -0.09
    iams
    -0.09
    eus
    -0.09
    erals
    -0.09
     Eleven
    -0.08
    utions
    -0.08
    ands
    -0.08
    POSITIVE LOGITS
     ratt
    0.14
    ting
    0.12
     rat
    0.11
    ionale
    0.11
     poison
    0.11
    icate
    0.10
     RAT
    0.10
     Rational
    0.10
    cline
    0.10
     Rat
    0.10
    Activations Density 0.043%

    No Known Activations