© 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. 26433
    Prev
    Next
    INDEX
    Explanations

    have to + verb

    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
     somehow
    -0.10
     coord
    -0.09
     monitoring
    -0.09
     cooper
    -0.09
     patience
    -0.08
     ASAP
    -0.08
     maxim
    -0.08
    uild
    -0.08
     careful
    -0.08
     dy
    -0.08
    POSITIVE LOGITS
     disappoint
    0.10
     Hex
    0.10
    apis
    0.10
     conclude
    0.10
     adm
    0.10
     hex
    0.10
     admire
    0.10
    legate
    0.10
     sadly
    0.10
     abandon
    0.09
    Activations Density 0.086%

    No Known Activations