© 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. 114290
    Prev
    Next
    INDEX
    Explanations

    revered, idol, mythical, worship

    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
     joy
    -0.12
    ussen
    -0.12
    unset
    -0.11
     RSVP
    -0.11
     contrary
    -0.11
    Inline
    -0.11
     screams
    -0.11
     disple
    -0.10
     Sadd
    -0.10
     pessim
    -0.10
    POSITIVE LOGITS
     revered
    0.24
     idol
    0.23
     mythical
    0.23
     myth
    0.21
     unreachable
    0.21
     mythology
    0.20
     reverence
    0.20
     worsh
    0.19
     mystical
    0.19
     mysterious
    0.19
    Activations Density 0.215%

    No Known Activations