© 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. 4191
    Prev
    Next
    INDEX
    Explanations

    unit, size, or quantity 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
     emoji
    -0.11
     selfie
    -0.11
     sortable
    -0.10
     ðĿ
    -0.10
     бÑĥд
    -0.10
     bip
    -0.09
     crown
    -0.09
    [from
    -0.09
    emoji
    -0.09
     selfies
    -0.09
    POSITIVE LOGITS
    ordo
    0.10
     Orch
    0.09
     Nap
    0.09
    .sap
    0.08
     confined
    0.08
     Overs
    0.08
     discret
    0.08
     Women
    0.08
    ecz
    0.08
    ruta
    0.08
    Activations Density 0.007%

    No Known Activations