© 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. 26838
    Prev
    Next
    INDEX
    Explanations

    into a positionin a relationshipinto troubleinto a dilemmaunder the wrongin charge of

    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
     unab
    -0.10
    ays
    -0.09
     Tage
    -0.08
    aten
    -0.08
     bpp
    -0.08
     presence
    -0.08
    variably
    -0.07
    én
    -0.07
    -peer
    -0.07
     decidedly
    -0.07
    POSITIVE LOGITS
     verge
    0.14
     trouble
    0.11
     mood
    0.11
    licer
    0.11
    ÑĥÑĢÑģ
    0.10
     dilemma
    0.10
     rampage
    0.10
     hurry
    0.10
     conclusions
    0.10
     troubles
    0.10
    Activations Density 0.103%

    No Known Activations