© 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. 113426
    Prev
    Next
    INDEX
    Explanations

    interjections and odd characters

    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
     Sith
    -0.10
     ."
    -0.09
    'R
    -0.09
     Rao
    -0.09
    chez
    -0.09
    yon
    -0.08
     Kv
    -0.08
     Darth
    -0.08
    'C
    -0.08
     rez
    -0.08
    POSITIVE LOGITS
    ~
    0.12
    OUCH
    0.12
    ~,
    0.12
    ~~~~
    0.11
    ãĢľ
    0.11
    pha
    0.10
     ~
    0.10
     Petra
    0.10
    ï½ŀ
    0.10
    ~~~~~~~~
    0.09
    Activations Density 0.004%

    No Known Activations