© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 30580
    Prev
    Next
    INDEX
    Explanations

    places, groups, colors

    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
    anter
    -0.09
     perman
    -0.09
    visibility
    -0.09
    orz
    -0.08
     quint
    -0.08
    _fid
    -0.08
    dish
    -0.08
    /AP
    -0.08
     NS
    -0.08
    avras
    -0.08
    POSITIVE LOGITS
     finally
    0.41
    finally
    0.33
     eventually
    0.28
     Finally
    0.26
    Finally
    0.24
     ultimately
    0.24
    	finally
    0.22
     Eventually
    0.20
     eventual
    0.20
    Eventually
    0.18
    Activations Density 0.037%

    No Known Activations