© 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. 17958
    Prev
    Next
    INDEX
    Explanations

    k followed by 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
    ekt
    -0.12
    Ú©
    -0.12
    oux
    -0.11
    indi
    -0.11
    eya
    -0.11
    ey
    -0.11
    illis
    -0.10
    eam
    -0.10
    ylko
    -0.10
    egra
    -0.10
    POSITIVE LOGITS
    aepernick
    0.20
    ollectors
    0.19
    haled
    0.17
    rieg
    0.17
    ernels
    0.15
    inesis
    0.15
    night
    0.14
    ết
    0.13
    etchup
    0.13
    rypton
    0.12
    Activations Density 0.280%

    No Known Activations