© 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. 6248
    Prev
    Next
    INDEX
    Explanations

    part of 'must regard' or 'strongly affected'

    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
     realtime
    -0.14
     alot
    -0.13
     ...
    -0.13
     effected
    -0.11
     ....
    -0.10
     decidedly
    -0.10
    adan
    -0.10
    ½
    -0.10
     --
    -0.10
    variably
    -0.10
    POSITIVE LOGITS
     dra
    0.16
     practise
    0.16
     adore
    0.15
     programmes
    0.15
     pals
    0.15
     pricey
    0.15
     programme
    0.14
     frequently
    0.14
     youngster
    0.14
    0.14
    Activations Density 0.395%

    No Known Activations