© 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. 33058
    Prev
    Next
    INDEX
    Explanations

    exactly, identical, or precise match

    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
     Finch
    -0.10
     synerg
    -0.09
     ultimately
    -0.09
     Eli
    -0.09
     diffuse
    -0.09
     permanently
    -0.09
     assertNull
    -0.09
     crush
    -0.09
     sob
    -0.09
     Elliot
    -0.08
    POSITIVE LOGITS
     exactly
    0.52
     exact
    0.52
     Exact
    0.44
     identical
    0.43
    exact
    0.41
    Exact
    0.39
     Exactly
    0.36
    Exactly
    0.34
     precisely
    0.32
    _exact
    0.31
    Activations Density 1.110%

    No Known Activations