© 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. 32117
    Prev
    Next
    INDEX
    Explanations

    how hard can it be

    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
     Abram
    -0.09
    akens
    -0.09
     Oc
    -0.09
     gras
    -0.08
     Bolt
    -0.08
     playable
    -0.08
    -ok
    -0.08
    imos
    -0.08
    amat
    -0.08
    ewe
    -0.08
    POSITIVE LOGITS
     can
    0.15
    Can
    0.14
    can
    0.13
    	can
    0.13
     Can
    0.13
     CAN
    0.12
    .can
    0.12
    _can
    0.12
    CAN
    0.12
    CanBe
    0.11
    Activations Density 0.073%

    No Known Activations