© 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. 50211
    Prev
    Next
    INDEX
    Explanations

    want, need, or ought to

    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
     prototypes
    -0.09
    antan
    -0.09
    ka
    -0.09
    IJ
    -0.09
     nond
    -0.08
     skewed
    -0.08
    ickle
    -0.08
    aud
    -0.08
     rulings
    -0.08
     Rey
    -0.08
    POSITIVE LOGITS
    /ge
    0.10
     Cycl
    0.09
    -relative
    0.09
     slu
    0.09
    cycl
    0.09
    bef
    0.09
     Perr
    0.08
    -ts
    0.08
     Matthias
    0.08
     fkk
    0.08
    Activations Density 0.002%

    No Known Activations