© 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. 88830
    Prev
    Next
    INDEX
    Explanations

    shipping details, privacy, or questions

    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
     Occ
    -0.11
    transport
    -0.10
    ucz
    -0.10
     ebay
    -0.09
     transporting
    -0.09
     boo
    -0.09
    aaaaaaaa
    -0.09
    Transport
    -0.09
     skype
    -0.09
     attachment
    -0.09
    POSITIVE LOGITS
     discreet
    0.19
     stealth
    0.14
     Stealth
    0.13
     Confidential
    0.12
     anonym
    0.12
     discretion
    0.12
     discret
    0.12
     confidential
    0.12
     exped
    0.12
     Privacy
    0.11
    Activations Density 0.049%

    No Known Activations