© 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. 17855
    Prev
    Next
    INDEX
    Explanations

    Institute of

    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
    aiser
    -0.10
    ACES
    -0.10
     flyer
    -0.09
     lasc
    -0.09
     anecdotes
    -0.09
     Trick
    -0.09
     Flames
    -0.09
     rejo
    -0.09
    bos
    -0.09
    /Grid
    -0.09
    POSITIVE LOGITS
     Hust
    0.10
     Pike
    0.09
    967
    0.09
    óst
    0.09
     Primitive
    0.09
     Cottage
    0.09
    anon
    0.08
     subtype
    0.08
     forward
    0.08
    á»ĥ
    0.08
    Activations Density 0.175%

    No Known Activations