© 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. 27119
    Prev
    Next
    INDEX
    Explanations

    spouse or companion

    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
     teammates
    -0.09
     grouping
    -0.09
     wife
    -0.08
     colleagues
    -0.08
    :-
    -0.08
     partner
    -0.08
     esper
    -0.07
     Partner
    -0.07
     servants
    -0.07
     others
    -0.07
    POSITIVE LOGITS
    ä¸İ
    0.20
     åĴĮ
    0.17
    ìĻĢ
    0.16
    åĴĮ
    0.14
    ê³¼
    0.14
     vs
    0.13
    _vs
    0.13
     myself
    0.13
     mutually
    0.12
    -vs
    0.12
    Activations Density 0.079%

    No Known Activations