© 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. 47678
    Prev
    Next
    INDEX
    Explanations

    unsupported browser or disabled features

    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
     IMO
    -0.14
     admittedly
    -0.13
     reportedly
    -0.12
     IM
    -0.11
     Tone
    -0.11
     understandably
    -0.11
    ulle
    -0.11
     arguably
    -0.11
    IMO
    -0.10
    unt
    -0.10
    POSITIVE LOGITS
    —that
    0.13
     Pact
    0.10
     Gale
    0.09
    -that
    0.09
    ço
    0.08
     PR
    0.08
    <td
    0.08
     Crack
    0.08
     cal
    0.08
    iful
    0.08
    Activations Density 1.030%

    No Known Activations