© 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. 47463
    Prev
    Next
    INDEX
    Explanations

    like other

    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
     admittedly
    -0.12
    EMS
    -0.09
     obviously
    -0.09
     purposely
    -0.08
     anymore
    -0.08
    _Post
    -0.08
     McCl
    -0.08
     Kimber
    -0.08
     evidently
    -0.08
    ç¨
    -0.08
    POSITIVE LOGITS
     aj
    0.10
     preceded
    0.10
    anja
    0.10
     plenty
    0.10
     disproportionate
    0.10
    xxx
    0.09
    ny
    0.09
    ville
    0.09
    here
    0.09
     lots
    0.09
    Activations Density 0.303%

    No Known Activations