© 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. 47193
    Prev
    Next
    INDEX
    Explanations

    take off / out

    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
     into
    -0.15
    into
    -0.15
    Into
    -0.14
    _into
    -0.13
    onto
    -0.13
     onto
    -0.13
    hw
    -0.12
    YRO
    -0.12
     obliv
    -0.12
    vern
    -0.12
    POSITIVE LOGITS
    eder
    0.08
     carefully
    0.08
     circulation
    0.07
     Shi
    0.07
     peg
    0.07
    oub
    0.07
    ataka
    0.07
     Stap
    0.07
    egen
    0.07
    rok
    0.07
    Activations Density 0.012%

    No Known Activations