© 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. 27014
    Prev
    Next
    INDEX
    Explanations

    don't know

    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
     appraisal
    -0.12
     unaware
    -0.11
    IGH
    -0.10
     Apprec
    -0.10
     Ethi
    -0.10
     Forgot
    -0.10
     apprec
    -0.10
     Definitely
    -0.09
     shift
    -0.09
     (__
    -0.09
    POSITIVE LOGITS
     golf
    0.11
     consequential
    0.10
     brave
    0.10
     gol
    0.09
     recall
    0.09
    ↵   ↵
    0.09
     CLAIM
    0.09
     fetish
    0.09
     fanc
    0.09
    emie
    0.09
    Activations Density 0.114%

    No Known Activations