© 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. 17505
    Prev
    Next
    INDEX
    Explanations

    without or not

    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
     WITHOUT
    -0.13
    hausen
    -0.12
    unread
    -0.12
    agem
    -0.12
     unread
    -0.11
    upp
    -0.11
     sess
    -0.11
    stride
    -0.11
    tensor
    -0.11
     undefeated
    -0.11
    POSITIVE LOGITS
     whatsoever
    0.19
     yet
    0.14
    yet
    0.12
     anymore
    0.12
     nor
    0.11
     but
    0.10
     sondern
    0.10
    /non
    0.09
     WHATSOEVER
    0.09
     or
    0.08
    Activations Density 0.407%

    No Known Activations