© 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. 48409
    Prev
    Next
    INDEX
    Explanations

    and specifications

    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
     yet
    -0.13
    aria
    -0.12
    Yet
    -0.11
    ات
    -0.11
    inha
    -0.11
     Turnbull
    -0.11
    yet
    -0.11
     Yet
    -0.10
    ATAL
    -0.10
     Flores
    -0.10
    POSITIVE LOGITS
    zym
    0.09
    oga
    0.08
    yre
    0.08
     perv
    0.08
    OTH
    0.08
    aser
    0.08
    è§ģ
    0.08
    odes
    0.08
    bare
    0.08
     Marin
    0.08
    Activations Density 0.057%

    No Known Activations