© 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. 7279
    Prev
    Next
    INDEX
    Explanations

    laden with

    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
     Bust
    -0.10
    tit
    -0.10
     Fucked
    -0.09
    ond
    -0.09
    VI
    -0.09
     confined
    -0.09
    appy
    -0.08
     resizable
    -0.08
     INCLUDED
    -0.08
     Stateless
    -0.08
    POSITIVE LOGITS
     irony
    0.16
     steep
    0.14
     secrecy
    0.13
     heavily
    0.12
     emotion
    0.12
    laden
    0.12
     nostalgia
    0.12
     desperation
    0.11
     nep
    0.11
     layers
    0.11
    Activations Density 0.047%

    No Known Activations