© 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. 32966
    Prev
    Next
    INDEX
    Explanations

    Carl SSON

    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
    ycz
    -0.09
     Juliet
    -0.08
    eln
    -0.08
    ellar
    -0.08
     fas
    -0.08
     outings
    -0.08
     sincerely
    -0.08
     admired
    -0.08
    Sketch
    -0.08
    lis
    -0.08
    POSITIVE LOGITS
    isle
    0.22
    otta
    0.19
    sson
    0.15
    ifornia
    0.14
    ota
    0.13
    strom
    0.13
    ston
    0.13
    ton
    0.12
    itos
    0.12
    otty
    0.11
    Activations Density 0.020%

    No Known Activations