© 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. 18033
    Prev
    Next
    INDEX
    Explanations

    conditions following "with"

    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
     slip
    -0.09
    unk
    -0.08
     Jennings
    -0.08
     Beg
    -0.07
    esc
    -0.07
     background
    -0.07
     Hob
    -0.07
    abee
    -0.07
     homosexual
    -0.07
     begun
    -0.07
    POSITIVE LOGITS
     vagina
    0.13
     wax
    0.12
     vul
    0.12
     anne
    0.11
     cerv
    0.11
     uterus
    0.11
     ovar
    0.11
    959
    0.11
    ssa
    0.10
     nipples
    0.10
    Activations Density 0.040%

    No Known Activations