© 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. 17711
    Prev
    Next
    INDEX
    Explanations

    being alone or single

    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
     backstage
    -0.12
    veyor
    -0.11
     penetrating
    -0.10
     Enc
    -0.10
     emitting
    -0.10
     Kauf
    -0.10
     stall
    -0.10
    -bin
    -0.10
     Teh
    -0.09
    avit
    -0.09
    POSITIVE LOGITS
     lonely
    0.17
     loneliness
    0.15
     babys
    0.14
     Alone
    0.13
     boredom
    0.13
     alone
    0.13
    -alone
    0.12
     bored
    0.12
     fend
    0.12
     lon
    0.11
    Activations Density 0.035%

    No Known Activations