© 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. 47258
    Prev
    Next
    INDEX
    Explanations

    red/black combinations

    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
    Tumblr
    -0.10
    Prostit
    -0.09
    china
    -0.08
    instagram
    -0.07
    paypal
    -0.07
    Interstitial
    -0.06
    cli
    -0.06
     Salon
    -0.06
    Vue
    -0.06
     itself
    -0.06
    POSITIVE LOGITS
    _Lean
    0.16
    ofire
    0.16
    _Master
    0.15
    _marshall
    0.15
    _chan
    0.15
    _Anim
    0.14
    _Osc
    0.14
    inator
    0.14
    _Collections
    0.14
    Guy
    0.14
    Activations Density 0.192%

    No Known Activations