© 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. 15127
    Prev
    Next
    INDEX
    Explanations

    depending on how

    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
     puta
    -0.08
    -share
    -0.08
     intend
    -0.08
     premium
    -0.07
     reclaimed
    -0.07
     =&
    -0.07
     Kurt
    -0.07
    ku
    -0.07
     excelente
    -0.07
     Why
    -0.07
    POSITIVE LOGITS
     how
    0.15
     luck
    0.13
    ÑģÑĭ
    0.12
     Luck
    0.12
     spacing
    0.11
     whether
    0.11
     reaction
    0.11
     viewpoint
    0.11
     HOW
    0.11
     turnout
    0.11
    Activations Density 0.015%

    No Known Activations