© 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. 31778
    Prev
    Next
    INDEX
    Explanations

    electrostatic, untamed, three-toed, transcendent

    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
     Likes
    -0.10
    odash
    -0.10
     Hubb
    -0.10
     shred
    -0.09
     indeb
    -0.08
     JsonRequest
    -0.08
    oyal
    -0.08
    <|endoftext|>
    -0.08
    raries
    -0.08
     gramm
    -0.08
    POSITIVE LOGITS
    bk
    0.09
     Cornel
    0.09
     Sem
    0.08
     Reid
    0.08
    :</
    0.08
     Ned
    0.08
     Pad
    0.08
    net
    0.08
    cbc
    0.08
    abler
    0.08
    Activations Density 0.038%

    No Known Activations