© 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. 15807
    Prev
    Next
    INDEX
    Explanations

    news or events occurring

    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
    annis
    -0.10
    anoia
    -0.10
    ange
    -0.10
     Loft
    -0.09
    gons
    -0.09
     GAM
    -0.09
    aos
    -0.09
     Gareth
    -0.09
    JECT
    -0.09
     Pillow
    -0.09
    POSITIVE LOGITS
     barriers
    0.18
     apart
    0.13
     barrier
    0.13
     boundaries
    0.13
     breaking
    0.11
     down
    0.11
     dawn
    0.11
     silence
    0.11
    dance
    0.11
     Barrier
    0.10
    Activations Density 0.041%

    No Known Activations