© 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. 6361
    Prev
    Next
    INDEX
    Explanations

    web inspector Safari

    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
    er
    -0.10
     ingress
    -0.08
    —at
    -0.08
     Tay
    -0.08
    ini
    -0.07
     mote
    -0.07
    erot
    -0.07
    ASH
    -0.07
    ifo
    -0.07
    å¢
    -0.07
    POSITIVE LOGITS
     Laz
    0.12
     sic
    0.11
     laz
    0.11
     Fir
    0.11
     backwards
    0.10
    sic
    0.10
    /is
    0.10
    alam
    0.10
    Gal
    0.10
     fir
    0.09
    Activations Density 0.003%

    No Known Activations