© 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. 115871
    Prev
    Next
    INDEX
    Explanations

    60-63 or numbers

    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
    fang
    -0.10
     Reese
    -0.09
     Thorn
    -0.09
     Rena
    -0.08
     TN
    -0.08
     narc
    -0.08
    ptive
    -0.08
     badge
    -0.08
    olley
    -0.08
     sworn
    -0.07
    POSITIVE LOGITS
    62
    0.14
    61
    0.14
    ĕ
    0.14
     sixty
    0.13
    63
    0.13
    >>>>>>>
    0.12
    60
    0.12
    	   ↵
    0.12
     PDT
    0.11
     Bergen
    0.11
    Activations Density 0.684%

    No Known Activations