© 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. 6129
    Prev
    Next
    INDEX
    Explanations

    introduce myself

    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
     Entries
    -0.09
     $#
    -0.09
     Ri
    -0.09
     confront
    -0.09
    pone
    -0.09
     fatt
    -0.09
    де
    -0.09
     polarization
    -0.08
    -Origin
    -0.08
     admitting
    -0.08
    POSITIVE LOGITS
     call
    0.28
     Call
    0.23
    call
    0.23
    Call
    0.21
    称
    0.18
     shortened
    0.17
    (call
    0.17
    -call
    0.16
     abbreviated
    0.16
    _call
    0.16
    Activations Density 0.045%

    No Known Activations