© 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. 89807
    Prev
    Next
    INDEX
    Explanations

    it followed by comma

    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
    ITER
    -0.12
    енÑĭ
    -0.11
    OTES
    -0.11
    Their
    -0.11
     earthqu
    -0.11
     mogul
    -0.11
     our
    -0.11
    aso
    -0.11
    their
    -0.11
    TimeString
    -0.11
    POSITIVE LOGITS
     it
    0.46
     It
    0.36
    It
    0.32
     its
    0.26
    ,it
    0.25
     Its
    0.25
    _it
    0.24
    Its
    0.24
    	it
    0.24
    	It
    0.23
    Activations Density 1.465%

    No Known Activations