© 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. 5227
    Prev
    Next
    INDEX
    Explanations

    qualitative analysis using interviews

    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
     simplistic
    -0.11
     Various
    -0.10
     presumably
    -0.10
    Interestingly
    -0.10
     supposedly
    -0.10
    estone
    -0.10
     Interestingly
    -0.10
    asso
    -0.10
     billions
    -0.10
     Crud
    -0.10
    POSITIVE LOGITS
     qualitative
    0.23
     qual
    0.18
     pilot
    0.16
     interviews
    0.16
     Qual
    0.15
     descriptive
    0.15
    Qual
    0.15
     semi
    0.14
     grounded
    0.14
     ethn
    0.14
    Activations Density 9.734%

    No Known Activations