© 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. 25502
    Prev
    Next
    INDEX
    Explanations

    heightened needs, Partition, affect, other cultures

    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
     mankind
    -0.18
     youngster
    -0.12
    -vs
    -0.11
     :-
    -0.11
     subconscious
    -0.11
     pointless
    -0.11
     independ
    -0.11
     viewpoints
    -0.10
     manpower
    -0.10
     mindset
    -0.10
    POSITIVE LOGITS
     privile
    0.25
     neoliberal
    0.23
     mediated
    0.20
     foreground
    0.20
     “[
    0.20
     spaces
    0.18
     narratives
    0.18
     heg
    0.18
     Fou
    0.17
     mascul
    0.17
    Activations Density 0.841%

    No Known Activations