© 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. 29831
    Prev
    Next
    INDEX
    Explanations

    T followed by 2, DD, ain, anne, itled, ov, obar, ertiary

    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
    ag
    -0.13
    him
    -0.12
    oes
    -0.12
    ollectors
    -0.12
    oi
    -0.12
    ask
    -0.12
    ile
    -0.12
    lect
    -0.11
    ozo
    -0.11
    RI
    -0.11
    POSITIVE LOGITS
    jejer
    0.22
    itledBorder
    0.15
     rex
    0.14
    issue
    0.14
    -shirts
    0.13
    utorials
    0.13
    -shirt
    0.13
    shirt
    0.13
    rolley
    0.13
    upper
    0.13
    Activations Density 0.279%

    No Known Activations