© 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. 114894
    Prev
    Next
    INDEX
    Explanations

    short of

    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
     Loren
    -0.12
     tre
    -0.09
     Arnold
    -0.09
    fid
    -0.09
     meanwhile
    -0.09
    adb
    -0.08
    opa
    -0.08
     sympath
    -0.08
    inst
    -0.08
    Taken
    -0.08
    POSITIVE LOGITS
     short
    0.25
     shy
    0.24
     shortfall
    0.23
     missing
    0.20
     close
    0.20
    short
    0.19
     Close
    0.19
     lacking
    0.19
     Short
    0.19
    -short
    0.18
    Activations Density 0.187%

    No Known Activations