© 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. 114173
    Prev
    Next
    INDEX
    Explanations

    predicting, differentiating, detecting accurately

    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
     resend
    -0.11
     presenting
    -0.10
     obligatory
    -0.10
     Resp
    -0.10
     investigated
    -0.10
    rit
    -0.10
    quette
    -0.10
     grind
    -0.10
     inconvenient
    -0.10
     convenient
    -0.09
    POSITIVE LOGITS
     detecting
    0.26
     identifying
    0.25
     accurately
    0.25
     Detect
    0.23
     predicting
    0.23
     spotting
    0.22
     identification
    0.22
     ability
    0.22
     accuracy
    0.22
     detection
    0.22
    Activations Density 0.875%

    No Known Activations