© 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. 5262
    Prev
    Next
    INDEX
    Explanations

    achieve desired

    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
    #from
    -0.09
    asan
    -0.09
    vor
    -0.09
     Ult
    -0.09
    629
    -0.09
     cud
    -0.09
    erais
    -0.09
     Tent
    -0.09
    ìĦ
    -0.09
     Carp
    -0.09
    POSITIVE LOGITS
     desired
    0.34
    desired
    0.24
     intended
    0.23
     Desired
    0.22
     needed
    0.21
     accompl
    0.21
     wanted
    0.19
     required
    0.19
     what
    0.19
     necessary
    0.19
    Activations Density 0.532%

    No Known Activations