© 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. 28472
    Prev
    Next
    INDEX
    Explanations

    in or to a

    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
    lest
    -0.08
    _pres
    -0.08
    742
    -0.08
    ahn
    -0.08
     Bang
    -0.07
    499
    -0.07
    UB
    -0.07
    onom
    -0.07
     showing
    -0.07
     Sunshine
    -0.07
    POSITIVE LOGITS
    ordinate
    0.11
     escalate
    0.11
    eling
    0.10
    gone
    0.10
    eneral
    0.10
     entr
    0.10
    emer
    0.09
    .Protocol
    0.09
     unfold
    0.09
    laces
    0.09
    Activations Density 0.501%

    No Known Activations