© 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. 7922
    Prev
    Next
    INDEX
    Explanations

    leaks and extortion

    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
     Lub
    -0.11
     masc
    -0.10
     carnival
    -0.10
    _lot
    -0.10
     Dia
    -0.09
     visiting
    -0.09
     Bers
    -0.09
     refl
    -0.09
     travelling
    -0.09
     Blond
    -0.09
    POSITIVE LOGITS
     leaked
    0.21
     blackmail
    0.18
     leaks
    0.17
     footage
    0.17
     extortion
    0.17
     tapes
    0.16
     videos
    0.15
     hacked
    0.15
     nude
    0.15
     leak
    0.15
    Activations Density 0.124%

    No Known Activations