© 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. 46964
    Prev
    Next
    INDEX
    Explanations

    effect of

    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
    alian
    -0.08
    /dis
    -0.08
    ight
    -0.08
    ulis
    -0.08
     skies
    -0.08
    illes
    -0.08
    alion
    -0.08
    Descri
    -0.07
     Mostly
    -0.07
    enn
    -0.07
    POSITIVE LOGITS
    æŀľ
    0.14
     effic
    0.14
     eff
    0.14
     effective
    0.13
    uez
    0.13
     ineffective
    0.12
     effectively
    0.12
    effective
    0.12
     aver
    0.12
     outr
    0.11
    Activations Density 0.085%

    No Known Activations