© 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. 7203
    Prev
    Next
    INDEX
    Explanations

    he/him

    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
     herself
    -0.26
     myself
    -0.16
     lesbian
    -0.15
     maternity
    -0.15
     gratuita
    -0.15
     elle
    -0.15
     Latina
    -0.13
     themselves
    -0.13
     ourselves
    -0.13
     yourselves
    -0.13
    POSITIVE LOGITS
     himself
    0.66
     his
    0.38
    —he
    0.35
     Himself
    0.34
    his
    0.33
     коÑĤоÑĢÑĭй
    0.27
    /her
    0.25
    ä»ĸ
    0.23
    His
    0.23
    /she
    0.22
    Activations Density 5.858%

    No Known Activations