© 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. 5379
    Prev
    Next
    INDEX
    Explanations

    will not or wont

    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
    efe
    -0.09
     proved
    -0.08
    avers
    -0.08
    eti
    -0.08
     configur
    -0.08
     Barker
    -0.07
    egg
    -0.07
    esti
    -0.07
     upro
    -0.07
     equip
    -0.07
    POSITIVE LOGITS
     tolerate
    0.13
    /c
    0.12
     ACCEPT
    0.12
     Accept
    0.11
     accept
    0.11
     dow
    0.11
     ALLOW
    0.11
    accept
    0.10
     knowingly
    0.10
     recurring
    0.10
    Activations Density 0.091%

    No Known Activations