© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    same following words

    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
    bes
    -0.12
     reap
    -0.10
    á»
    -0.10
    inx
    -0.10
    neys
    -0.10
     EXTRA
    -0.10
    ture
    -0.09
    loc
    -0.09
    tings
    -0.09
     morale
    -0.09
    POSITIVE LOGITS
     nationality
    0.11
     initials
    0.10
     Difference
    0.10
    /op
    0.10
    ParameterValue
    0.10
     unchanged
    0.09
     species
    0.09
     milieu
    0.09
     Different
    0.09
    dif
    0.09
    Activations Density 0.063%

    No Known Activations