© 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. 113090
    Prev
    Next
    INDEX
    Explanations

    . 500 80 rim Number Null in 's

    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
     POSIX
    -0.12
     pissed
    -0.11
     perch
    -0.11
     dick
    -0.11
     asshole
    -0.11
     fucking
    -0.11
     {%
    -0.10
     bitch
    -0.10
     parole
    -0.10
     evil
    -0.10
    POSITIVE LOGITS
     tremend
    0.09
     âĢ»
    0.08
    IZER
    0.08
     strugg
    0.08
     ...(
    0.08
    /Framework
    0.07
     Stranger
    0.07
    ;;;;
    0.07
    	short
    0.07
    uli
    0.07
    Activations Density 0.005%

    No Known Activations