© 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. 47761
    Prev
    Next
    INDEX
    Explanations

    say that

    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
     Haram
    -0.12
    eki
    -0.11
     steril
    -0.11
     Towers
    -0.11
    Dep
    -0.10
     depress
    -0.10
    _VC
    -0.10
    imal
    -0.10
    dep
    -0.10
     Crab
    -0.09
    POSITIVE LOGITS
     confidently
    0.30
     honestly
    0.28
     conscience
    0.23
     sincerely
    0.22
     legitimately
    0.21
     unequiv
    0.20
     conscient
    0.19
     truth
    0.19
     honesty
    0.18
     confidence
    0.18
    Activations Density 0.119%

    No Known Activations