© 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. 14586
    Prev
    Next
    INDEX
    Explanations

    No matter

    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
    rp
    -0.09
     whit
    -0.08
    ench
    -0.08
     execut
    -0.08
    irl
    -0.08
     skinny
    -0.08
     Wag
    -0.07
     cach
    -0.07
     Scha
    -0.07
     reput
    -0.07
    POSITIVE LOGITS
     words
    0.14
     doubt
    0.13
     signs
    0.12
     escaping
    0.12
    avail
    0.12
    grily
    0.11
    aval
    0.11
     spoken
    0.11
     response
    0.11
     additional
    0.11
    Activations Density 0.016%

    No Known Activations