© 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. 90858
    Prev
    Next
    INDEX
    Explanations

    to public needs and sharing

    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
     Fif
    -0.12
     firstly
    -0.12
     Firstly
    -0.12
     Newsp
    -0.11
     erst
    -0.11
    anst
    -0.11
     ALSO
    -0.11
    Perm
    -0.11
     molest
    -0.11
     condos
    -0.11
    POSITIVE LOGITS
    Insp
    0.09
     Lon
    0.08
     aesthetic
    0.07
     Ze
    0.07
     trust
    0.07
     Zen
    0.07
     geographical
    0.07
     geographic
    0.07
    venge
    0.07
     financial
    0.07
    Activations Density 0.313%

    No Known Activations