© 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. 26551
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by conjunctions/contrasts

    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
    tics
    -0.10
    anches
    -0.10
    than
    -0.09
     coupled
    -0.09
     Umb
    -0.09
     Coco
    -0.09
     nad
    -0.09
    AMI
    -0.09
    chan
    -0.09
    ç´ł
    -0.09
    POSITIVE LOGITS
     anymore
    0.19
    yet
    0.15
     yet
    0.13
    orz
    0.12
    unless
    0.12
     merely
    0.12
     unless
    0.11
     Unless
    0.11
     nor
    0.10
    lew
    0.10
    Activations Density 0.079%

    No Known Activations