© 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. 90543
    Prev
    Next
    INDEX
    Explanations

    First thing, introduction, example

    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
    olle
    -0.11
    orate
    -0.10
     there
    -0.10
    oir
    -0.10
    reds
    -0.09
    uppe
    -0.09
    uggy
    -0.09
    there
    -0.09
    ROL
    -0.09
    imity
    -0.09
    POSITIVE LOGITS
     Impress
    0.11
     impressions
    0.10
     up
    0.09
     things
    0.09
    (Have
    0.09
     hym
    0.09
     cert
    0.09
     Beaut
    0.08
     recip
    0.08
    ican
    0.08
    Activations Density 0.002%

    No Known Activations