© 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. 27299
    Prev
    Next
    INDEX
    Explanations

    album titles and descriptions

    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
    abus
    -0.10
    @student
    -0.10
     vX
    -0.10
     <->
    -0.09
    ought
    -0.09
     shouldBe
    -0.09
    zed
    -0.09
     infer
    -0.09
     puta
    -0.09
     parc
    -0.09
    POSITIVE LOGITS
     another
    0.12
     designed
    0.10
     pleased
    0.09
     shorthand
    0.09
     an
    0.09
    another
    0.09
     dim
    0.09
     proud
    0.08
     based
    0.08
     a
    0.08
    Activations Density 0.318%

    No Known Activations