© 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. 30354
    Prev
    Next
    INDEX
    Explanations

    envelope

    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
    fulness
    -0.11
    rooms
    -0.11
    vik
    -0.10
    aining
    -0.10
    forth
    -0.10
    lobber
    -0.10
    .googleapis
    -0.10
    ############
    -0.10
    ards
    -0.10
    esses
    -0.10
    POSITIVE LOGITS
    pon
    0.10
    ophon
    0.09
     flap
    0.09
    icious
    0.09
    ëĭĪëĭ¤
    0.09
    æĻ¯
    0.08
     pry
    0.08
    ä½ĵ
    0.08
    pee
    0.08
    ÑĤоÑĢ
    0.08
    Activations Density 0.010%

    No Known Activations