© 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. 33632
    Prev
    Next
    INDEX
    Explanations

    something is not working

    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
     undoubtedly
    -0.15
     arguably
    -0.14
     probably
    -0.13
     essentially
    -0.12
     basically
    -0.11
     sounding
    -0.11
    aland
    -0.11
     unmistak
    -0.11
     admittedly
    -0.10
     unequiv
    -0.10
    POSITIVE LOGITS
     somehow
    0.17
     judging
    0.12
     lately
    0.11
     Somehow
    0.11
     magically
    0.10
     effortlessly
    0.10
     strangely
    0.10
     endless
    0.10
    aura
    0.10
     mirac
    0.10
    Activations Density 0.316%

    No Known Activations