© 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. 32399
    Prev
    Next
    INDEX
    Explanations

    another or others

    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
     Ingram
    -0.10
    949
    -0.10
     {_
    -0.10
    DEX
    -0.10
     tuo
    -0.10
    án
    -0.10
     yourself
    -0.09
    /custom
    -0.09
    ãĤģ
    -0.09
    ENSE
    -0.09
    POSITIVE LOGITS
     others
    0.30
    others
    0.23
     another
    0.21
     Others
    0.21
    Others
    0.19
     Another
    0.17
    another
    0.16
    Another
    0.15
     equally
    0.13
     smaller
    0.11
    Activations Density 0.453%

    No Known Activations