© 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. 6617
    Prev
    Next
    INDEX
    Explanations

    H names

    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
    ello
    -0.12
    ackers
    -0.11
    ome
    -0.11
    asher
    -0.11
    ash
    -0.11
    ook
    -0.10
    andler
    -0.10
    arda
    -0.10
    rait
    -0.10
    ung
    -0.10
    POSITIVE LOGITS
    ERSHEY
    0.27
    su
    0.18
    rus
    0.16
     pyl
    0.16
    wang
    0.15
    rab
    0.15
    sing
    0.15
    sie
    0.15
    ruby
    0.15
    irsch
    0.15
    Activations Density 0.292%

    No Known Activations