© 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. 25367
    Prev
    Next
    INDEX
    Explanations

    If you

    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
    Ñģки
    -0.10
    ware
    -0.09
     overshadow
    -0.09
     territorial
    -0.08
    Plus
    -0.08
     Gong
    -0.08
    icl
    -0.08
    boo
    -0.08
    eron
    -0.08
    phia
    -0.07
    POSITIVE LOGITS
     ifs
    0.14
    rame
    0.11
     EVER
    0.11
    tek
    0.10
     ever
    0.10
    rai
    0.10
     imitation
    0.10
     oppos
    0.10
    reur
    0.10
     silence
    0.09
    Activations Density 0.064%

    No Known Activations