© 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. 4571
    Prev
    Next
    INDEX
    Explanations

    references to indirect mentions

    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
     metall
    -0.10
    777
    -0.09
     femin
    -0.08
    apel
    -0.08
     synchron
    -0.08
    itan
    -0.08
     Valent
    -0.08
     Hort
    -0.08
     nar
    -0.08
     defect
    -0.08
    POSITIVE LOGITS
     implied
    0.22
     mild
    0.17
     indirect
    0.17
     implicit
    0.16
     references
    0.16
     implication
    0.15
     References
    0.15
     mentions
    0.15
     IMPLIED
    0.15
     mention
    0.15
    Activations Density 0.051%

    No Known Activations