© 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. 28460
    Prev
    Next
    INDEX
    Explanations

    this latest installment

    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
     interv
    -0.12
     famed
    -0.12
     famous
    -0.11
     notorious
    -0.11
     infamous
    -0.11
     sworn
    -0.10
     renowned
    -0.10
     trailing
    -0.10
     moderator
    -0.10
     Gesch
    -0.10
    POSITIVE LOGITS
     installment
    0.14
     latest
    0.13
     tale
    0.13
     timely
    0.13
     excellent
    0.12
     sleeper
    0.11
     premiere
    0.11
     enjoyable
    0.11
     debut
    0.11
     outing
    0.11
    Activations Density 0.309%

    No Known Activations