© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 26831
    Prev
    Next
    INDEX
    Explanations

    Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć, Szczeć

    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
    emer
    -0.11
     Aj
    -0.10
     Morg
    -0.10
     slippery
    -0.10
    aille
    -0.10
     Settlement
    -0.10
     sided
    -0.10
     Barg
    -0.10
    pace
    -0.09
    ede
    -0.09
    POSITIVE LOGITS
    ¯¯¯¯
    0.08
    afari
    0.08
    reh
    0.08
     conjug
    0.08
     minib
    0.08
     herself
    0.08
    /light
    0.08
    ervals
    0.07
     Seah
    0.07
     inference
    0.07
    Activations Density 0.001%

    No Known Activations