© 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. 33034
    Prev
    Next
    INDEX
    Explanations

    large quantities

    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
    pit
    -0.10
    vier
    -0.10
     Dane
    -0.10
    zá
    -0.10
    /member
    -0.10
     CIS
    -0.10
    eki
    -0.09
     Ramp
    -0.09
     meas
    -0.09
     Caul
    -0.09
    POSITIVE LOGITS
     (>
    0.32
     (~
    0.20
     relative
    0.17
     compared
    0.15
    /high
    0.15
     (<
    0.13
    (~
    0.13
     indeed
    0.12
    relative
    0.12
    /fast
    0.11
    Activations Density 0.546%

    No Known Activations