© 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. 31540
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns + body part

    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
     Touch
    -0.08
     Ultimate
    -0.08
    mp
    -0.08
     MacDonald
    -0.08
    allowed
    -0.08
    Touch
    -0.08
    root
    -0.07
    AQ
    -0.07
     Bent
    -0.07
     touch
    -0.07
    POSITIVE LOGITS
    bart
    0.12
     tortured
    0.12
     gaze
    0.11
     (++
    0.11
     attention
    0.11
     Charg
    0.11
    efa
    0.11
     prostit
    0.10
     Nin
    0.10
     fragile
    0.10
    Activations Density 0.007%

    No Known Activations