© 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. 14522
    Prev
    Next
    INDEX
    Explanations

    following text snippets

    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
     halfway
    -0.12
    awa
    -0.10
     midpoint
    -0.10
    /win
    -0.10
    contents
    -0.10
     unl
    -0.10
     setback
    -0.09
    odia
    -0.09
     midway
    -0.09
    /inc
    -0.09
    POSITIVE LOGITS
     sentence
    0.25
     sentences
    0.23
    sentence
    0.17
     statement
    0.16
     Sentence
    0.16
    entence
    0.15
    _sentence
    0.14
    Sentence
    0.13
     paragraph
    0.13
     clause
    0.13
    Activations Density 0.050%

    No Known Activations