© 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. 32436
    Prev
    Next
    INDEX
    Explanations

    crooked teeth, tilted cap, eccentric binaries

    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
     ponto
    -0.08
     drip
    -0.08
    /res
    -0.08
     pit
    -0.08
     bou
    -0.08
     deco
    -0.08
     subt
    -0.08
     conventional
    -0.08
     sexism
    -0.08
     Ala
    -0.08
    POSITIVE LOGITS
    ness
    0.15
     grin
    0.13
     Smile
    0.12
    ahoma
    0.12
     finger
    0.11
     smile
    0.11
     alignment
    0.11
     alignments
    0.11
    kk
    0.11
     fingers
    0.11
    Activations Density 0.003%

    No Known Activations