© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48380
    Prev
    Next
    INDEX
    Explanations

    going or went 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
    ivent
    -0.11
    uchi
    -0.11
    inka
    -0.11
    /start
    -0.10
    ibil
    -0.10
    hic
    -0.09
    arrass
    -0.09
    ambi
    -0.09
    _embed
    -0.09
    otate
    -0.09
    POSITIVE LOGITS
     bye
    0.17
     Bye
    0.14
     goes
    0.14
     Goes
    0.13
     goodbye
    0.13
     gotta
    0.13
     stays
    0.11
    bye
    0.11
     priority
    0.10
    onto
    0.10
    Activations Density 0.094%

    No Known Activations