© 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. 26465
    Prev
    Next
    INDEX
    Explanations

    sharing link IM

    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
    ":-
    -0.11
     strained
    -0.11
     plur
    -0.10
     VIP
    -0.10
     rejecting
    -0.09
     rejected
    -0.09
    alom
    -0.09
     magistrate
    -0.09
    nas
    -0.09
    aptcha
    -0.09
    POSITIVE LOGITS
     sharing
    0.21
     Sharing
    0.20
     share
    0.20
     Share
    0.19
     shares
    0.18
    -sharing
    0.17
    åĪĨ享
    0.17
    share
    0.16
     Shares
    0.16
     SHARE
    0.16
    Activations Density 0.355%

    No Known Activations