© 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. 90238
    Prev
    Next
    INDEX
    Explanations

    talk discussion and questions

    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
    awi
    -0.10
    uba
    -0.09
    rij
    -0.08
     suggested
    -0.08
     drill
    -0.08
    egend
    -0.08
     numbered
    -0.08
    -ce
    -0.08
     greetings
    -0.08
     resc
    -0.08
    POSITIVE LOGITS
     privately
    0.13
     about
    0.12
     Alone
    0.12
     urgently
    0.12
    about
    0.11
    ankan
    0.11
     About
    0.11
     upstairs
    0.10
     ASAP
    0.10
     alone
    0.10
    Activations Density 0.030%

    No Known Activations