© 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. 15290
    Prev
    Next
    INDEX
    Explanations

    attachment-related words

    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
    igt
    -0.11
    ingroup
    -0.10
    Abb
    -0.09
    wo
    -0.09
     Gib
    -0.09
    issy
    -0.09
    ATOR
    -0.09
    amp
    -0.09
    ìĹ´
    -0.09
    ific
    -0.08
    POSITIVE LOGITS
    ments
    0.16
    BaseContext
    0.14
    ements
    0.14
    arya
    0.14
    _fu
    0.14
    ement
    0.13
     attaches
    0.12
    Detach
    0.12
    ment
    0.12
    -det
    0.11
    Activations Density 0.047%

    No Known Activations