© 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. 33431
    Prev
    Next
    INDEX
    Explanations

    expresses how something makes me feel or think

    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
    emade
    -0.11
     intimid
    -0.10
    erate
    -0.10
    onn
    -0.10
     arrang
    -0.10
    ador
    -0.09
     intox
    -0.09
     reve
    -0.09
    entially
    -0.09
    )did
    -0.09
    POSITIVE LOGITS
     unable
    0.17
     behave
    0.16
     feel
    0.16
     appear
    0.15
     lose
    0.15
     incapable
    0.14
     go
    0.14
     ineligible
    0.14
     able
    0.13
     come
    0.13
    Activations Density 0.043%

    No Known Activations