© 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. 7035
    Prev
    Next
    INDEX
    Explanations

    redeem, redemption, redevelopment

    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
    grand
    -0.11
     grandfather
    -0.10
    ish
    -0.09
    ngth
    -0.09
    rb
    -0.09
     Sho
    -0.08
    cht
    -0.08
     Sting
    -0.08
    UR
    -0.08
    lh
    -0.08
    POSITIVE LOGITS
     redeem
    0.14
     rede
    0.13
     Rede
    0.12
    able
    0.12
     Redemption
    0.12
     redemption
    0.11
     redeemed
    0.11
     reunited
    0.09
     Wend
    0.09
     remodel
    0.09
    Activations Density 0.050%

    No Known Activations