© 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. 30411
    Prev
    Next
    INDEX
    Explanations

    digit of

    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
    ffa
    -0.11
     Nolan
    -0.11
    eldom
    -0.10
     sog
    -0.10
     Firm
    -0.10
    }catch
    -0.10
    agu
    -0.10
    staking
    -0.10
    Submitting
    -0.10
     appar
    -0.10
    POSITIVE LOGITS
     disc
    0.09
     visibility
    0.08
     ol
    0.08
    öl
    0.07
     Glam
    0.07
     sense
    0.07
    letic
    0.07
     blackout
    0.07
    ader
    0.07
    sense
    0.07
    Activations Density 0.002%

    No Known Activations