© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 117606
    Prev
    Next
    INDEX
    Explanations

    names ending in ov

    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
    Negative Logits
     rel
    -0.09
     defenses
    -0.08
     dar
    -0.08
     sno
    -0.08
     seated
    -0.08
    ahun
    -0.08
    off
    -0.08
     Sno
    -0.08
     sens
    -0.08
    ient
    -0.08
    POSITIVE LOGITS
    sk
    0.16
    itch
    0.14
    ski
    0.13
    s
    0.11
    sz
    0.11
    t
    0.10
     Conversion
    0.10
     suffice
    0.10
    ITCH
    0.10
    etch
    0.10
    Activations Density 0.052%

    No Known Activations