© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48840
    Prev
    Next
    INDEX
    Explanations

    looking for clues or answers

    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
     Obt
    -0.11
    andr
    -0.10
    orz
    -0.10
     Nearby
    -0.10
     Benn
    -0.09
     Brilliant
    -0.09
     Klein
    -0.09
    ortex
    -0.09
    aben
    -0.09
     Haw
    -0.09
    POSITIVE LOGITS
     suitable
    0.21
     clues
    0.16
     any
    0.15
     anything
    0.15
     Suitable
    0.14
     signs
    0.13
     eligible
    0.13
     hints
    0.12
     usable
    0.12
     possible
    0.12
    Activations Density 0.136%

    No Known Activations