© 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. 113724
    Prev
    Next
    INDEX
    Explanations

    **but** followed by a contrasting statement

    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
     also
    -0.14
     nowhere
    -0.13
     not
    -0.13
     none
    -0.13
     NOT
    -0.12
     неÑĤ
    -0.12
     também
    -0.12
     unfortunately
    -0.11
     ALSO
    -0.11
    Unfortunately
    -0.11
    POSITIVE LOGITS
     certainly
    0.13
    omm
    0.12
     nor
    0.11
     sondern
    0.11
    nor
    0.11
     Certainly
    0.10
     Plenty
    0.10
    unic
    0.10
     submar
    0.09
    Certainly
    0.09
    Activations Density 0.097%

    No Known Activations