© 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. 113160
    Prev
    Next
    INDEX
    Explanations

    from

    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
    uum
    -0.11
     Catal
    -0.10
    Æ°á»
    -0.10
     Mile
    -0.10
     lump
    -0.10
    ibus
    -0.09
    mile
    -0.09
     eyebrow
    -0.09
    _RA
    -0.09
     discount
    -0.09
    POSITIVE LOGITS
     from
    0.29
    -from
    0.25
     From
    0.24
    ä»İ
    0.24
     FROM
    0.24
    from
    0.22
    From
    0.22
    _from
    0.22
     desde
    0.21
     backwards
    0.21
    Activations Density 0.423%

    No Known Activations