© 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. 90162
    Prev
    Next
    INDEX
    Explanations

    in [location/topic]

    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
     stakes
    -0.09
    seau
    -0.08
     invent
    -0.08
    ibraltar
    -0.08
     albeit
    -0.08
     Chow
    -0.07
     trainers
    -0.07
    ivent
    -0.07
     Robbie
    -0.07
     unr
    -0.07
    POSITIVE LOGITS
     nutshell
    0.12
     spotlight
    0.11
     Modern
    0.11
     Relation
    0.11
    /libs
    0.10
     broader
    0.10
    elsen
    0.10
     spotted
    0.10
    anse
    0.10
     modern
    0.09
    Activations Density 0.462%

    No Known Activations