© 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. 31242
    Prev
    Next
    INDEX
    Explanations

    it should

    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
     who
    -0.18
    who
    -0.16
     whom
    -0.10
     meta
    -0.09
     multim
    -0.09
    (cf
    -0.09
     contingent
    -0.09
    urat
    -0.09
     Catalog
    -0.09
     Who
    -0.09
    POSITIVE LOGITS
     itself
    0.18
     its
    0.15
     Its
    0.14
    its
    0.14
    Its
    0.14
    åħ¶
    0.12
    inq
    0.09
     pov
    0.09
     Boyd
    0.09
     which
    0.09
    Activations Density 0.050%

    No Known Activations