© 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. 17633
    Prev
    Next
    INDEX
    Explanations

    ass shaped, muscle cells, aa sequence

    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
    dek
    -0.09
    otten
    -0.09
    osti
    -0.09
    akt
    -0.09
     Couch
    -0.08
    isty
    -0.08
    ABCDE
    -0.08
    arios
    -0.08
    arena
    -0.08
    isl
    -0.08
    POSITIVE LOGITS
    -che
    0.12
     cheek
    0.11
     cheeks
    0.10
    -heavy
    0.10
    omens
    0.10
     enorme
    0.10
     mort
    0.09
    /screen
    0.09
     unin
    0.09
    anine
    0.09
    Activations Density 0.003%

    No Known Activations