© 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. 26138
    Prev
    Next
    INDEX
    Explanations

    appetite for

    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
     Bah
    -0.10
    ASE
    -0.09
    FM
    -0.09
    WF
    -0.09
     bah
    -0.09
     masa
    -0.08
     buoy
    -0.08
    lichkeit
    -0.08
     reserve
    -0.08
    Bah
    -0.08
    POSITIVE LOGITS
     success
    0.12
     destruction
    0.11
     knowledge
    0.11
     adventure
    0.11
     adversity
    0.10
     compliments
    0.10
     Thom
    0.09
     punishment
    0.09
     Adventure
    0.09
     controversy
    0.09
    Activations Density 0.009%

    No Known Activations