© 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. 114294
    Prev
    Next
    INDEX
    Explanations

    on demand

    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
     essentially
    -0.13
    ote
    -0.11
     basically
    -0.10
    787
    -0.10
    onga
    -0.10
     shapes
    -0.10
     vaguely
    -0.10
     arrog
    -0.10
    haus
    -0.09
     shaping
    -0.09
    POSITIVE LOGITS
     cue
    0.13
     rehe
    0.12
     timed
    0.11
     triggered
    0.11
     sensing
    0.11
     Hier
    0.11
     Cue
    0.10
     synchronized
    0.10
    ruc
    0.10
    confirm
    0.10
    Activations Density 0.014%

    No Known Activations