© 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. 17665
    Prev
    Next
    INDEX
    Explanations

    code block start or punctuation

    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
     till
    -0.11
     ect
    -0.11
     VOID
    -0.10
     opt
    -0.10
     Till
    -0.10
     indeb
    -0.10
     fanatic
    -0.10
     Padding
    -0.09
     Spike
    -0.09
     Grimm
    -0.09
    POSITIVE LOGITS
     (“
    0.11
    verb
    0.08
     imperfect
    0.08
     backstory
    0.08
    kowski
    0.07
    ideshow
    0.07
     gn
    0.07
    maj
    0.07
     novel
    0.07
    č↵↵
    0.07
    Activations Density 0.037%

    No Known Activations