© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 7548
    Prev
    Next
    INDEX
    Explanations

    telling the truth

    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
    -0.12
     zwar
    -0.12
     not
    -0.11
     both
    -0.11
     NOT
    -0.11
     WITHOUT
    -0.10
     BOTH
    -0.10
     WHATSOEVER
    -0.10
    —not
    -0.10
     både
    -0.10
    POSITIVE LOGITS
     nonetheless
    0.10
     sheer
    0.09
     _
    0.09
     simply
    0.09
    olid
    0.08
     nevertheless
    0.08
     darn
    0.08
     suff
    0.08
     damn
    0.08
    oS
    0.08
    Activations Density 0.216%

    No Known Activations