© 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. 30341
    Prev
    Next
    INDEX
    Explanations

    tell, give, explain, list

    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
     vale
    -0.10
    rieve
    -0.10
    arte
    -0.09
    dna
    -0.09
     vested
    -0.08
    aid
    -0.08
    gem
    -0.08
     Vale
    -0.08
     Yo
    -0.08
    quer
    -0.08
    POSITIVE LOGITS
     briefly
    0.17
    Tell
    0.15
     Tell
    0.15
     tell
    0.15
     describe
    0.13
     please
    0.13
    tell
    0.13
     Describe
    0.13
    Describe
    0.12
    describe
    0.12
    Activations Density 0.101%

    No Known Activations