© 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. 30281
    Prev
    Next
    INDEX
    Explanations

    watch video links

    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
    ule
    -0.11
    uts
    -0.11
     sounding
    -0.11
    orc
    -0.11
    /ay
    -0.10
    ament
    -0.10
    è®®
    -0.10
    handlers
    -0.10
    arks
    -0.10
    ities
    -0.10
    POSITIVE LOGITS
    /list
    0.22
    ?v
    0.19
     closely
    0.15
    tower
    0.14
    /read
    0.14
    (es
    0.12
    /he
    0.12
    able
    0.11
    fulness
    0.11
    /part
    0.10
    Activations Density 0.026%

    No Known Activations