© 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. 48855
    Prev
    Next
    INDEX
    Explanations

    creators and artists

    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
    FLOW
    -0.10
     administrator
    -0.09
     Dancing
    -0.09
    benh
    -0.09
     itself
    -0.09
    管çIJĨåijĺ
    -0.08
     arresting
    -0.08
    (flow
    -0.08
     personals
    -0.08
     operator
    -0.08
    POSITIVE LOGITS
     who
    0.22
     whom
    0.21
    who
    0.19
     whose
    0.18
    /auth
    0.16
    whose
    0.15
    -produ
    0.14
    /groups
    0.13
    /vendors
    0.12
     specializing
    0.12
    Activations Density 0.478%

    No Known Activations