© 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. 49693
    Prev
    Next
    INDEX
    Explanations

    how can question

    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
     besides
    -0.12
    >čč↵
    -0.10
    Besides
    -0.09
     certainly
    -0.09
    zl
    -0.09
     lance
    -0.09
    hed
    -0.09
     Mobility
    -0.09
    izon
    -0.08
     mobility
    -0.08
    POSITIVE LOGITS
     possibly
    0.18
     Possibly
    0.16
    possibly
    0.14
     reconcile
    0.13
     be
    0.12
     consc
    0.12
     so
    0.11
     afford
    0.10
     POSS
    0.10
     claim
    0.10
    Activations Density 0.063%

    No Known Activations