© 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. 89390
    Prev
    Next
    INDEX
    Explanations

    sell it, find it, use it

    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
    Their
    -0.12
     migliori
    -0.12
    дÑĢеÑģ
    -0.12
    ITO
    -0.11
     @@
    -0.11
    .hh
    -0.11
     oggi
    -0.11
    TimeString
    -0.11
    ITES
    -0.11
    ITER
    -0.11
    POSITIVE LOGITS
     it
    0.43
     It
    0.19
     its
    0.18
    å®
    0.17
     them
    0.17
    	it
    0.17
    It
    0.15
     itm
    0.15
    _it
    0.14
    åħ¶
    0.14
    Activations Density 0.718%

    No Known Activations