© 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. 16650
    Prev
    Next
    INDEX
    Explanations

    locations or disused spaces

    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
     dow
    -0.11
     Platt
    -0.10
     convo
    -0.10
    weg
    -0.10
     каÑĢÑĤ
    -0.09
     ÙĤ
    -0.08
     visuals
    -0.08
    chl
    -0.08
    /light
    -0.08
    inka
    -0.08
    POSITIVE LOGITS
     bathroom
    0.21
     bushes
    0.21
     toilets
    0.21
     restroom
    0.20
     bathrooms
    0.20
     toilet
    0.19
     abandoned
    0.15
     woods
    0.15
     vacant
    0.14
     deserted
    0.14
    Activations Density 0.070%

    No Known Activations