© 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. 29060
    Prev
    Next
    INDEX
    Explanations

    web pages and documentation

    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
     obl
    -0.10
    اء
    -0.09
     sunk
    -0.08
     contraction
    -0.08
    AAAAAAAA
    -0.08
    riere
    -0.08
    sburg
    -0.08
    HostName
    -0.08
    AppName
    -0.08
     paperback
    -0.08
    POSITIVE LOGITS
     Zac
    0.08
    quota
    0.08
    lagen
    0.08
    Aj
    0.08
    uing
    0.08
     Slate
    0.08
    icter
    0.07
     Quint
    0.07
     Vern
    0.07
    _prefs
    0.07
    Activations Density 1.745%

    No Known Activations