© 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-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3824
    Prev
    Next
    INDEX
    Explanations

    harms and negative impact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     legal
    -0.11
     legally
    -0.10
    iae
    -0.10
    Legal
    -0.10
    mans
    -0.10
     Legal
    -0.10
     liability
    -0.10
     legality
    -0.09
    PE
    -0.09
     laws
    -0.09
    POSITIVE LOGITS
     harms
    0.09
     disproportionate
    0.09
     requested
    0.09
     applicant
    0.08
    anz
    0.08
     Applicant
    0.08
    JUST
    0.08
     proposed
    0.08
    Sensitive
    0.08
     REQUEST
    0.08
    Activations Density 0.274%

    No Known Activations