© 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. 4616
    Prev
    Next
    INDEX
    Explanations

    brand value

    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
    обÑĭ
    -0.09
    ieten
    -0.09
     weary
    -0.09
    egers
    -0.09
     elbow
    -0.08
    arth
    -0.08
    SOAP
    -0.08
     Geg
    -0.08
     adam
    -0.07
    chnitt
    -0.07
    POSITIVE LOGITS
    (E
    0.17
    /E
    0.14
     coli
    0.14
    (EC
    0.13
    [E
    0.13
    ymous
    0.12
    enment
    0.12
    /es
    0.11
    ablish
    0.11
    merce
    0.10
    Activations Density 2.285%

    No Known Activations