© 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. 15758
    Prev
    Next
    INDEX
    Explanations

    from the environment

    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
     WHATSOEVER
    -0.13
    eba
    -0.11
     Kear
    -0.11
     ....↵↵
    -0.11
    ilde
    -0.11
    _lex
    -0.10
     ?????
    -0.10
     DISP
    -0.10
    anco
    -0.10
    ints
    -0.10
    POSITIVE LOGITS
     rather
    0.22
    —not
    0.17
     *
    0.16
    rather
    0.16
     BOTH
    0.15
     Rather
    0.15
     _
    0.15
     NOT
    0.14
     specifically
    0.14
     entire
    0.13
    Activations Density 0.512%

    No Known Activations