© 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. 30162
    Prev
    Next
    INDEX
    Explanations

    unlike

    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
     convoy
    -0.09
    Avatar
    -0.09
     until
    -0.09
    gon
    -0.09
    lich
    -0.08
     Avatar
    -0.08
    fid
    -0.08
     Theo
    -0.08
    until
    -0.08
     Til
    -0.08
    POSITIVE LOGITS
     which
    0.31
    which
    0.27
     whose
    0.23
     коÑĤоÑĢ
    0.22
     wich
    0.20
    whose
    0.20
     WHICH
    0.20
     коÑĤоÑĢÑĭй
    0.20
     who
    0.20
     where
    0.19
    Activations Density 0.482%

    No Known Activations