© 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. 7700
    Prev
    Next
    INDEX
    Explanations

    hitting 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
     Jain
    -0.10
    midd
    -0.10
    XS
    -0.09
    elon
    -0.09
    å¤
    -0.09
    jam
    -0.09
     Helpers
    -0.09
    522
    -0.09
    atto
    -0.09
    797
    -0.09
    POSITIVE LOGITS
     shit
    0.18
     fan
    0.15
     rubber
    0.15
     crap
    0.15
    shit
    0.14
     proverb
    0.14
     hits
    0.13
     hitting
    0.13
     Rubber
    0.12
    fan
    0.12
    Activations Density 0.028%

    No Known Activations