© 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. 14467
    Prev
    Next
    INDEX
    Explanations

    make you or your

    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
    redo
    -0.10
    ree
    -0.10
     liking
    -0.09
     carte
    -0.09
     Brun
    -0.09
    nev
    -0.09
    egan
    -0.09
    andy
    -0.09
     synonym
    -0.09
    artin
    -0.09
    POSITIVE LOGITS
     hardened
    0.15
     Charity
    0.11
     charity
    0.10
     stones
    0.10
     anyone
    0.10
     anybody
    0.10
     tough
    0.10
     angels
    0.10
     stone
    0.09
     Harden
    0.09
    Activations Density 0.041%

    No Known Activations