© 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
    2. Olmo-3-1125-32B
    3. 32-RES-BATCHTOPK-131K
    4. 88605
    Prev
    Next
    INDEX
    Explanations

    legal and music references

    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
    198
    -0.23
     Reagan
    -0.21
     Thatcher
    -0.16
    199
    -0.16
     AIDS
    -0.14
     punk
    -0.12
     cassette
    -0.11
     Clinton
    -0.11
     synth
    -0.11
     EEPROM
    -0.10
    POSITIVE LOGITS
    196
    0.30
     psychedelic
    0.22
     hipp
    0.18
     Beatles
    0.17
     psyched
    0.16
     Vietnam
    0.16
     Viet
    0.16
    Viet
    0.14
     Dylan
    0.14
     Psy
    0.14
    Activations Density 0.935%

    No Known Activations