© 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. 27805
    Prev
    Next
    INDEX
    Explanations

    lists of items separated by 'and' or 'or'

    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
     the
    -0.09
     certain
    -0.07
    itel
    -0.07
     various
    -0.07
    esi
    -0.07
    &amp
    -0.07
    itti
    -0.06
     Glasses
    -0.06
    <hr
    -0.05
    ‘s
    -0.05
    POSITIVE LOGITS
     modal
    0.13
    dae
    0.12
     moden
    0.12
     hereby
    0.12
    ECH
    0.12
     sooner
    0.11
     handful
    0.11
    affen
    0.11
    ulla
    0.11
    ixo
    0.11
    Activations Density 0.320%

    No Known Activations