© 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. 50280
    Prev
    Next
    INDEX
    Explanations

    doesn't mean

    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
    chin
    -0.13
     chin
    -0.11
     cheated
    -0.10
     Salt
    -0.09
     palms
    -0.09
     salt
    -0.09
    nell
    -0.08
     Briggs
    -0.08
     Deals
    -0.08
     Rem
    -0.08
    POSITIVE LOGITS
     deter
    0.24
     prevent
    0.22
     prevented
    0.22
     prevents
    0.22
     preventing
    0.21
     deterrent
    0.21
     Prevent
    0.20
     hind
    0.20
     didn
    0.20
     stop
    0.19
    Activations Density 0.159%

    No Known Activations