© 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. 30018
    Prev
    Next
    INDEX
    Explanations

    right there

    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
    gor
    -0.08
     Gor
    -0.08
     Gould
    -0.07
     Sa
    -0.07
     Nu
    -0.07
    cw
    -0.06
     Perez
    -0.06
     chase
    -0.06
     Vor
    -0.06
     infl
    -0.06
    POSITIVE LOGITS
     right
    0.25
    right
    0.20
     RIGHT
    0.18
    Right
    0.16
     Right
    0.15
    (right
    0.14
    _right
    0.14
    	right
    0.14
    olla
    0.14
    ,right
    0.14
    Activations Density 0.125%

    No Known Activations