© 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. 115279
    Prev
    Next
    INDEX
    Explanations

    your option

    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
    sti
    -0.10
     carg
    -0.09
     payload
    -0.08
    shaw
    -0.08
    orda
    -0.08
    Ñİ
    -0.08
     positional
    -0.08
     payloads
    -0.08
    obs
    -0.08
     at
    -0.07
    POSITIVE LOGITS
     discretion
    0.19
     disposal
    0.17
     urging
    0.15
     expense
    0.15
     fingertips
    0.14
     peril
    0.14
     doorstep
    0.14
     request
    0.14
     mercy
    0.14
     convenience
    0.13
    Activations Density 0.050%

    No Known Activations