© 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. 7489
    Prev
    Next
    INDEX
    Explanations

    "hate or love" / "fix it" / "drop it"

    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
    anch
    -0.11
     ide
    -0.11
    isin
    -0.10
    ANCH
    -0.09
    hores
    -0.09
    thal
    -0.09
     TZ
    -0.09
     Hoch
    -0.09
    ffi
    -0.09
     nada
    -0.09
    POSITIVE LOGITS
    >čč↵
    0.11
    erde
    0.09
    uling
    0.09
     Hue
    0.09
    utow
    0.09
    lla
    0.08
     till
    0.08
    udit
    0.08
     Invalidate
    0.08
     seams
    0.08
    Activations Density 0.006%

    No Known Activations