© 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. 112588
    Prev
    Next
    INDEX
    Explanations

    letting go and clinging

    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
    Porno
    -0.10
     Mash
    -0.09
    hb
    -0.09
     Sno
    -0.09
    dl
    -0.09
    Gap
    -0.09
    hsi
    -0.09
     pronounce
    -0.08
    [@
    -0.08
    ufe
    -0.08
    POSITIVE LOGITS
     control
    0.16
     attachments
    0.16
     attachment
    0.15
     Control
    0.15
     clinging
    0.13
     CONTROL
    0.13
     tightly
    0.13
    /release
    0.13
    Control
    0.13
     cling
    0.13
    Activations Density 0.013%

    No Known Activations