© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 14664
    Prev
    Next
    INDEX
    Explanations

    statement is

    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
    èµ·
    -0.09
     Nom
    -0.09
     undecided
    -0.08
     Pros
    -0.08
    pike
    -0.08
     Wend
    -0.08
     advantages
    -0.08
     Guys
    -0.08
     attract
    -0.08
    gaard
    -0.08
    POSITIVE LOGITS
     Segment
    0.12
     incomplete
    0.11
     segment
    0.11
     stripper
    0.11
     imagery
    0.10
    ouro
    0.10
     neglect
    0.10
     umbrella
    0.10
     Viv
    0.10
     misses
    0.10
    Activations Density 0.001%

    No Known Activations