© 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. 26848
    Prev
    Next
    INDEX
    Explanations

    easy, difficult, manageable, welcome

    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
     forbidden
    -0.08
    privation
    -0.08
     env
    -0.08
     Woo
    -0.08
    rox
    -0.08
     Welfare
    -0.08
     fortunes
    -0.08
     Franco
    -0.08
     Env
    -0.08
     Thread
    -0.08
    POSITIVE LOGITS
     easy
    0.28
     easier
    0.26
     doc
    0.25
    easy
    0.24
     easiest
    0.23
     obedient
    0.22
     submissive
    0.22
     willing
    0.21
     receptive
    0.21
     trainable
    0.21
    Activations Density 0.103%

    No Known Activations