© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    called / referring to

    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
    alone
    -0.11
     Chandler
    -0.10
     PREF
    -0.09
     McN
    -0.09
     entirety
    -0.09
     Wool
    -0.09
     unle
    -0.09
     alone
    -0.09
    icare
    -0.09
    _hard
    -0.09
    POSITIVE LOGITS
     because
    0.19
    because
    0.16
     referring
    0.14
     porque
    0.14
    åĽł
    0.12
     karena
    0.11
     since
    0.10
     interchange
    0.10
     refers
    0.10
     parce
    0.10
    Activations Density 0.709%

    No Known Activations