© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 33841
    Prev
    Next
    INDEX
    Explanations

    ending with too

    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
     additionally
    -0.13
    also
    -0.12
    Also
    -0.12
     also
    -0.12
     Also
    -0.11
     ALSO
    -0.11
     también
    -0.11
     auch
    -0.10
     mayo
    -0.10
    caller
    -0.10
    POSITIVE LOGITS
    jah
    0.09
    tl
    0.09
    uru
    0.09
    utz
    0.08
    uple
    0.08
    iner
    0.08
    Banner
    0.08
     Ges
    0.08
     Chambers
    0.08
    isel
    0.08
    Activations Density 0.046%

    No Known Activations