© 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. 112385
    Prev
    Next
    INDEX
    Explanations

    no

    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
     disproportionately
    -0.11
    orse
    -0.10
     ultimately
    -0.10
    endif
    -0.10
     ||=
    -0.10
    _nl
    -0.10
     necessarily
    -0.09
    -lite
    -0.09
    ayer
    -0.09
     cautiously
    -0.09
    POSITIVE LOGITS
     no
    0.33
    no
    0.25
    (no
    0.22
     nothing
    0.22
    ä¸įåŃĺåľ¨
    0.22
    没æľī
    0.22
    	no
    0.20
     keine
    0.20
     неÑĤ
    0.19
     avoiding
    0.19
    Activations Density 0.662%

    No Known Activations