© 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. 4818
    Prev
    Next
    INDEX
    Explanations

    what doing

    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
     Mu
    -0.09
     mu
    -0.08
     Rounds
    -0.08
    abee
    -0.08
     spells
    -0.08
    uro
    -0.08
    inely
    -0.08
    olith
    -0.08
    loth
    -0.08
    rish
    -0.08
    POSITIVE LOGITS
     what
    0.17
     doing
    0.17
    what
    0.16
    doing
    0.16
    æŃ£åľ¨
    0.14
     Doing
    0.13
    Doing
    0.13
     youre
    0.12
     WHAT
    0.12
     tossing
    0.11
    Activations Density 0.079%

    No Known Activations