© 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. 16638
    Prev
    Next
    INDEX
    Explanations

    parts of the body and objects

    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
     measuring
    -0.09
     Higgins
    -0.08
     Berg
    -0.07
     programm
    -0.07
     Webster
    -0.07
     formulation
    -0.06
     Alias
    -0.06
     Ther
    -0.06
    eness
    -0.06
     Hyde
    -0.06
    POSITIVE LOGITS
     Sob
    0.13
     Resp
    0.12
    idden
    0.12
     Huff
    0.12
     Tide
    0.12
     tide
    0.11
     disgusted
    0.11
    emas
    0.11
    ipe
    0.11
     cleaner
    0.11
    Activations Density 0.004%

    No Known Activations