© 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. 47707
    Prev
    Next
    INDEX
    Explanations

    cyrillic 'a' followed by more cyrillic

    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
    osoph
    -0.10
    atk
    -0.10
    achie
    -0.10
    ocene
    -0.09
    odor
    -0.09
    enberg
    -0.09
    hz
    -0.08
    ema
    -0.08
    MMdd
    -0.08
     TP
    -0.08
    POSITIVE LOGITS
    nc
    0.13
    mb
    0.13
    merican
    0.12
    nd
    0.12
    ccording
    0.12
    ny
    0.11
    alysis
    0.11
    nt
    0.11
    udio
    0.11
    lt
    0.11
    Activations Density 0.029%

    No Known Activations