© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 48681
    Prev
    Next
    INDEX
    Explanations

    take a look

    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
     cad
    -0.07
    ael
    -0.07
    cha
    -0.07
    usher
    -0.07
     Mons
    -0.07
    ivo
    -0.07
    amas
    -0.06
    idis
    -0.06
     appar
    -0.06
     Type
    -0.06
    POSITIVE LOGITS
     seat
    0.17
     look
    0.16
     closer
    0.16
     stab
    0.16
     gamble
    0.15
     Seat
    0.15
     Cue
    0.15
     cue
    0.14
    seat
    0.14
    hold
    0.14
    Activations Density 0.024%

    No Known Activations