© 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. 90869
    Prev
    Next
    INDEX
    Explanations

    premium filtration

    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
     immac
    -0.10
     separators
    -0.10
     Salv
    -0.09
     Burton
    -0.09
     Tul
    -0.09
    cloak
    -0.09
     pareja
    -0.09
     Tib
    -0.09
    auty
    -0.09
    /sn
    -0.09
    POSITIVE LOGITS
     muscles
    0.27
     muscle
    0.26
     Muscle
    0.23
     muscular
    0.20
     exercise
    0.20
     exercising
    0.19
     exercised
    0.18
     exercises
    0.18
     Exercise
    0.17
     Mus
    0.16
    Activations Density 0.104%

    No Known Activations