© 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. 16165
    Prev
    Next
    INDEX
    Explanations

    low value, worthless, despised

    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
    ona
    -0.13
     gent
    -0.12
    ONA
    -0.11
     nerv
    -0.11
     cozy
    -0.10
     cosy
    -0.10
     boutique
    -0.10
     distress
    -0.10
     ambiguous
    -0.10
    ocket
    -0.10
    POSITIVE LOGITS
     worthless
    0.28
     lowest
    0.20
     insignificant
    0.19
     expend
    0.19
     trash
    0.19
     inferior
    0.19
     disposable
    0.18
     desp
    0.17
     garbage
    0.17
     dirt
    0.16
    Activations Density 0.112%

    No Known Activations