© 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. 92076
    Prev
    Next
    INDEX
    Explanations

    email addresses or contact information

    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
     physical
    -0.09
     proclamation
    -0.09
     prone
    -0.08
     edited
    -0.08
    Occurred
    -0.08
     physically
    -0.08
     Physical
    -0.08
    CAA
    -0.08
    @
    -0.08
     mediocre
    -0.07
    POSITIVE LOGITS
     address
    0.12
    mailto
    0.12
     Feedback
    0.11
     feedback
    0.11
    address
    0.11
    Feedback
    0.10
    icast
    0.10
    /avatar
    0.10
    åľ°åĿĢ
    0.10
     Armor
    0.10
    Activations Density 0.021%

    No Known Activations