© 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. 88106
    Prev
    Next
    INDEX
    Explanations

    Slade, Slumberland, Slash, Slag, Slack, Slain

    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
    ợ
    -0.09
     flawless
    -0.09
    á»iji
    -0.09
    orial
    -0.09
    lete
    -0.08
     flipped
    -0.08
    .WebDriver
    -0.08
     flaw
    -0.08
    ainties
    -0.08
     lace
    -0.08
    POSITIVE LOGITS
     Sl
    0.23
     sl
    0.21
    Sl
    0.21
    /sl
    0.18
     SL
    0.16
    -sl
    0.16
     Slug
    0.14
    sl
    0.13
    _sl
    0.13
     slugg
    0.13
    Activations Density 0.145%

    No Known Activations