© 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. 114862
    Prev
    Next
    INDEX
    Explanations

    percentages and dates

    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
    4
    -0.13
    8
    -0.12
    2
    -0.12
    00
    -0.11
    33
    -0.11
    24
    -0.11
    5
    -0.11
    32
    -0.11
    9
    -0.11
    6
    -0.10
    POSITIVE LOGITS
    âĢ²
    0.09
    âĢ³
    0.09
     thus
    0.09
     usable
    0.09
     Uhr
    0.09
    Ñıд
    0.08
    anal
    0.08
    otton
    0.08
    -required
    0.08
    onz
    0.08
    Activations Density 0.443%

    No Known Activations