© 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. 33048
    Prev
    Next
    INDEX
    Explanations

    meant to 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
    881
    -0.09
    reich
    -0.09
     Mush
    -0.08
     Crossing
    -0.08
     bic
    -0.08
    928
    -0.08
     vigorous
    -0.08
     indiscrim
    -0.07
     crossing
    -0.07
     frantic
    -0.07
    POSITIVE LOGITS
     tailor
    0.33
     perfect
    0.31
    perfect
    0.25
     Perfect
    0.25
     tailored
    0.24
     PERF
    0.24
    Perfect
    0.23
     perfectly
    0.22
     suited
    0.21
     destiny
    0.21
    Activations Density 0.188%

    No Known Activations