© 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. 90431
    Prev
    Next
    INDEX
    Explanations

    still, somewhat, always, pretty

    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
     baths
    -0.08
    ivant
    -0.08
    urm
    -0.08
     Cater
    -0.08
    orre
    -0.08
    ously
    -0.08
    antes
    -0.07
    /world
    -0.07
    ante
    -0.07
     blat
    -0.07
    POSITIVE LOGITS
     a
    0.14
     needing
    0.13
     able
    0.12
     no
    0.11
     an
    0.11
     enough
    0.11
     worth
    0.11
     hoping
    0.10
     something
    0.10
     impossible
    0.10
    Activations Density 0.107%

    No Known Activations