© 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. 90928
    Prev
    Next
    INDEX
    Explanations

    endearments and informal address

    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
    inci
    -0.11
    pcs
    -0.11
    @example
    -0.10
    jr
    -0.10
    ble
    -0.10
    pray
    -0.10
    Joe
    -0.10
    âĢ¦and
    -0.09
    IEWS
    -0.09
    forth
    -0.09
    POSITIVE LOGITS
     friend
    0.08
     condolences
    0.08
     Necklace
    0.08
    _dtype
    0.07
    ัà¸ļ
    0.07
     heav
    0.07
     strugg
    0.07
     bubb
    0.07
    oton
    0.07
     sorry
    0.07
    Activations Density 0.021%

    No Known Activations