© 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. 17520
    Prev
    Next
    INDEX
    Explanations

    is that

    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
    tras
    -0.10
    ignum
    -0.10
    lp
    -0.10
     Liberals
    -0.10
     deserves
    -0.10
     many
    -0.10
    ASP
    -0.09
     ihn
    -0.09
    vat
    -0.09
    ég
    -0.09
    POSITIVE LOGITS
    olated
    0.13
     it
    0.13
    abella
    0.13
    olation
    0.12
    aac
    0.12
    olate
    0.11
    landers
    0.11
    iah
    0.11
    lands
    0.10
    omers
    0.10
    Activations Density 0.134%

    No Known Activations