© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 114317
    Prev
    Next
    INDEX
    Explanations

    remove all / left to / what you

    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
     secret
    -0.09
     merry
    -0.09
    secret
    -0.09
     surrogate
    -0.08
    hap
    -0.08
     Chamber
    -0.08
    erm
    -0.08
    spy
    -0.08
     Lump
    -0.08
    SUR
    -0.08
    POSITIVE LOGITS
     Accent
    0.11
     masturbating
    0.11
     shit
    0.10
     imm
    0.10
     orphan
    0.10
     fuck
    0.09
     asshole
    0.09
     Gors
    0.09
     seldom
    0.09
     !"
    0.09
    Activations Density 0.110%

    No Known Activations