© 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. 29164
    Prev
    Next
    INDEX
    Explanations

    you're looking for clarification

    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
     Manit
    -0.09
     Zuk
    -0.09
    ither
    -0.09
     Transcript
    -0.08
     Clayton
    -0.08
    hid
    -0.08
    ahi
    -0.08
     hurt
    -0.07
     Hier
    -0.07
     Hit
    -0.07
    POSITIVE LOGITS
     confuse
    0.25
     confused
    0.25
     confusing
    0.23
     confusion
    0.23
     confl
    0.22
     mixing
    0.21
     mixed
    0.20
     mixes
    0.19
     Mixing
    0.18
    mix
    0.18
    Activations Density 0.234%

    No Known Activations