© 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. 47224
    Prev
    Next
    INDEX
    Explanations

    trashy

    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
    eon
    -0.10
     Liberties
    -0.10
     Rae
    -0.09
    ECT
    -0.09
     Lon
    -0.08
    hol
    -0.08
     Hos
    -0.08
    unnel
    -0.08
    electronics
    -0.08
    arrings
    -0.08
    POSITIVE LOGITS
    iness
    0.16
    y
    0.15
    ier
    0.13
    ily
    0.13
    able
    0.12
     talk
    0.12
    ened
    0.12
    iest
    0.12
    yb
    0.12
    iers
    0.11
    Activations Density 0.002%

    No Known Activations