© 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. 17646
    Prev
    Next
    INDEX
    Explanations

    2. Redistributions in binary form

    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
    kip
    -0.12
    âĢ¦it
    -0.11
    955
    -0.11
    ®,
    -0.10
     glac
    -0.10
    werk
    -0.10
    ited
    -0.10
    room
    -0.10
     CreateTable
    -0.10
    ided
    -0.09
    POSITIVE LOGITS
     infer
    0.09
    atra
    0.08
     Vol
    0.08
     Kam
    0.07
     Ho
    0.07
     frac
    0.07
     verbosity
    0.07
    acho
    0.07
     Singular
    0.07
     Laurie
    0.07
    Activations Density 0.003%

    No Known Activations