© 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. 27411
    Prev
    Next
    INDEX
    Explanations

    thethethethethethethethethethelastbackgroundturnchaptersworkmicrostaffsettingworkpackets

    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
     Unused
    -0.12
     Trad
    -0.10
     exact
    -0.10
    Playable
    -0.10
     Poss
    -0.10
     mend
    -0.09
     door
    -0.09
    role
    -0.09
    éŨ
    -0.09
     gates
    -0.09
    POSITIVE LOGITS
     pacing
    0.15
     pricing
    0.14
     lighting
    0.14
     graphics
    0.13
     quality
    0.13
     photography
    0.13
     prices
    0.12
     performances
    0.11
     prose
    0.11
     humor
    0.11
    Activations Density 0.163%

    No Known Activations