© 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. 30599
    Prev
    Next
    INDEX
    Explanations

    hard followed by specific words

    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
    118
    -0.08
    ish
    -0.08
    ULO
    -0.07
     Jensen
    -0.07
    sumer
    -0.07
     ruin
    -0.07
    erro
    -0.07
     emiss
    -0.07
    Violation
    -0.07
    ovich
    -0.07
    POSITIVE LOGITS
     hardcore
    0.16
    -hard
    0.15
     Hard
    0.15
    _hard
    0.15
     hard
    0.15
     hardcoded
    0.15
    Hard
    0.15
     HARD
    0.14
    copy
    0.14
    hard
    0.14
    Activations Density 0.026%

    No Known Activations