© 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. 18345
    Prev
    Next
    INDEX
    Explanations

    details and descriptions

    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
    mts
    -0.12
    steder
    -0.11
    ADR
    -0.10
    олÑĮз
    -0.10
    /API
    -0.09
     unlucky
    -0.09
     coordinated
    -0.09
     stead
    -0.09
    rlen
    -0.09
    erot
    -0.09
    POSITIVE LOGITS
    ALT
    0.07
    _COLL
    0.07
     Pascal
    0.07
     grand
    0.07
    (init
    0.07
     elabor
    0.07
    modal
    0.07
     multiplic
    0.07
    cloak
    0.07
     experiment
    0.07
    Activations Density 0.189%

    No Known Activations