© 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. 49787
    Prev
    Next
    INDEX
    Explanations

    currency symbols and special characters

    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
     undef
    -0.09
    éĥ
    -0.09
    iego
    -0.09
    Whats
    -0.08
    ilt
    -0.08
    owie
    -0.08
    actively
    -0.08
     allied
    -0.08
    ipro
    -0.08
    fm
    -0.08
    POSITIVE LOGITS
    ------------
    0.10
    -------------↵
    0.10
    _INET
    0.10
    IRST
    0.09
    ÑģÑı
    0.09
    ably
    0.09
    ---------------↵
    0.09
    errar
    0.09
    uthor
    0.09
     Consortium
    0.09
    Activations Density 0.077%

    No Known Activations