© 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. 113260
    Prev
    Next
    INDEX
    Explanations

    hard followed by a descriptive word

    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
    eli
    -0.11
     Rams
    -0.10
    VN
    -0.10
    ç¦
    -0.09
    leo
    -0.09
     aw
    -0.08
     Stra
    -0.08
     guide
    -0.08
     cripp
    -0.08
    rier
    -0.08
    POSITIVE LOGITS
     enough
    0.16
     Enough
    0.13
    -en
    0.11
    ocre
    0.11
    Enough
    0.11
    iks
    0.10
    iker
    0.10
    /fast
    0.09
     Santo
    0.09
     IGN
    0.09
    Activations Density 0.005%

    No Known Activations