© 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. 5130
    Prev
    Next
    INDEX
    Explanations

    gregory

    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
    AGO
    -0.10
     Wort
    -0.09
     mistaken
    -0.09
    ########
    -0.09
    etti
    -0.09
    minated
    -0.09
    ritt
    -0.09
    etta
    -0.09
    ©
    -0.09
    ettes
    -0.09
    POSITIVE LOGITS
    ory
    0.16
    orianCalendar
    0.16
    oire
    0.16
    orio
    0.15
    orian
    0.14
    arious
    0.13
    or
    0.13
    gles
    0.13
    gy
    0.13
    oria
    0.13
    Activations Density 0.041%

    No Known Activations