© 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. 31136
    Prev
    Next
    INDEX
    Explanations

    string if

    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
    наÑĩ
    -0.11
    /loading
    -0.10
     ensuing
    -0.10
     Gros
    -0.10
    marvin
    -0.09
    swick
    -0.09
    /not
    -0.09
    alt
    -0.09
     ti
    -0.09
     appearance
    -0.09
    POSITIVE LOGITS
     is
    0.13
     exists
    0.12
     occurs
    0.10
     impover
    0.09
     overturn
    0.09
     expires
    0.08
     meets
    0.08
    527
    0.08
     siÄĻ
    0.08
     intox
    0.08
    Activations Density 0.403%

    No Known Activations