© 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. 7574
    Prev
    Next
    INDEX
    Explanations

    parts of

    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
    akis
    -0.08
    ella
    -0.08
    678
    -0.07
     Stewart
    -0.07
    Handled
    -0.07
     bord
    -0.07
     Case
    -0.07
     Said
    -0.07
    act
    -0.07
    atto
    -0.07
    POSITIVE LOGITS
    	that
    0.12
    ót
    0.12
    that
    0.12
    iu
    0.12
     that
    0.12
    ale
    0.11
     which
    0.11
     wich
    0.11
    nger
    0.11
     ÑĩÑĤо
    0.10
    Activations Density 0.398%

    No Known Activations