© 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. 14986
    Prev
    Next
    INDEX
    Explanations

    fitting and focus

    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
    usk
    -0.11
    emo
    -0.10
    ussen
    -0.09
     purposely
    -0.08
     Equip
    -0.08
     Mul
    -0.08
     Sanctuary
    -0.08
     fragile
    -0.08
    orer
    -0.08
     dando
    -0.08
    POSITIVE LOGITS
     comfortably
    0.22
     without
    0.18
    without
    0.16
     fully
    0.16
     easily
    0.15
     WITHOUT
    0.14
     comfortable
    0.14
     reliably
    0.14
     satisf
    0.14
     ohne
    0.13
    Activations Density 0.222%

    No Known Activations