© 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. 113577
    Prev
    Next
    INDEX
    Explanations

    any whatsoever

    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
     immediately
    -0.13
     Certain
    -0.13
     certain
    -0.13
    Certain
    -0.12
     fully
    -0.12
     fairly
    -0.12
     immediate
    -0.12
     shortly
    -0.11
     several
    -0.11
     instantly
    -0.10
    POSITIVE LOGITS
     anything
    0.40
     whatsoever
    0.38
     anywhere
    0.36
    anything
    0.34
     any
    0.34
     nor
    0.33
     ANY
    0.31
    ä»»
    0.31
     Anything
    0.27
     anybody
    0.27
    Activations Density 0.645%

    No Known Activations