© 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. 28887
    Prev
    Next
    INDEX
    Explanations

    very + adjective

    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
    iet
    -0.09
    uto
    -0.09
     Easy
    -0.09
    alle
    -0.09
    idis
    -0.09
    inish
    -0.08
     overwhelming
    -0.08
    Easy
    -0.08
     unanimous
    -0.08
     indiscrim
    -0.08
    POSITIVE LOGITS
     audible
    0.13
     NOT
    0.13
     pii
    0.12
     NON
    0.12
     satisf
    0.11
    appropri
    0.11
     Thorn
    0.11
     decidedly
    0.11
     NS
    0.11
    -human
    0.11
    Activations Density 0.039%

    No Known Activations