© 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. 117177
    Prev
    Next
    INDEX
    Explanations

    should verb

    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
     unavoid
    -0.10
    hurst
    -0.08
    etsk
    -0.08
    akit
    -0.08
    /ag
    -0.08
    	ext
    -0.08
     sigma
    -0.08
     hom
    -0.08
    isor
    -0.08
     lifes
    -0.07
    POSITIVE LOGITS
     probably
    0.22
    probably
    0.17
     Probably
    0.16
    Probably
    0.16
     prol
    0.13
     prob
    0.12
     probs
    0.12
     mention
    0.11
     probable
    0.11
     clarify
    0.11
    Activations Density 0.018%

    No Known Activations