© 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. 89449
    Prev
    Next
    INDEX
    Explanations

    can't help myself

    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
     scand
    -0.14
     preferably
    -0.12
     Gould
    -0.11
     convin
    -0.11
    uin
    -0.10
     persuasion
    -0.10
    hek
    -0.10
     Cli
    -0.10
     ATL
    -0.10
    icha
    -0.09
    POSITIVE LOGITS
     being
    0.12
     having
    0.11
     anymore
    0.10
    eld
    0.10
     Feld
    0.10
     herself
    0.10
     tears
    0.10
     accord
    0.10
     Yourself
    0.09
     himself
    0.09
    Activations Density 0.001%

    No Known Activations