© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 16599
    Prev
    Next
    INDEX
    Explanations

    isn't it, don't you know, haven't i

    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
     ï
    -0.11
     demi
    -0.11
    gom
    -0.09
    -columns
    -0.09
    bih
    -0.09
    öh
    -0.09
     targeted
    -0.09
     perhaps
    -0.09
    ani
    -0.09
    ï
    -0.09
    POSITIVE LOGITS
     enough
    0.11
     Warn
    0.11
     supposed
    0.11
     barber
    0.10
     Arb
    0.10
     assez
    0.10
     realize
    0.10
     ashamed
    0.09
     Barber
    0.09
    esto
    0.09
    Activations Density 0.024%

    No Known Activations