© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 17069
    Prev
    Next
    INDEX
    Explanations

    names followed by a comma

    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
    sono
    -0.11
    .getContent
    -0.10
    (and
    -0.10
    [l
    -0.10
    occo
    -0.10
    ÙĬØ©
    -0.10
    abaj
    -0.09
     dyn
    -0.09
    /***/
    -0.09
    igi
    -0.09
    POSITIVE LOGITS
    —the
    0.37
    (the
    0.28
    -the
    0.26
    ,the
    0.25
    the
    0.20
     the
    0.17
    —a
    0.16
    	the
    0.16
    —one
    0.16
    _the
    0.16
    Activations Density 1.517%

    No Known Activations