© 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. 6533
    Prev
    Next
    INDEX
    Explanations

    even though

    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
     when
    -0.12
    å½ĵ
    -0.10
    when
    -0.10
    UINT
    -0.10
    	when
    -0.09
    chw
    -0.09
    alta
    -0.09
     cuando
    -0.09
     Vig
    -0.09
     When
    -0.09
    POSITIVE LOGITS
     me
    0.14
     hardened
    0.11
     my
    0.11
     myself
    0.11
     Yours
    0.11
     ourselves
    0.10
     Hop
    0.10
    ITH
    0.09
     standards
    0.09
    ifu
    0.09
    Activations Density 0.014%

    No Known Activations