© 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. 6811
    Prev
    Next
    INDEX
    Explanations

    inv followed by 'incible', 'itations', 'oking', 'as', 'isc'

    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
     monet
    -0.09
    ulle
    -0.08
    ief
    -0.07
    rots
    -0.07
     flair
    -0.07
     posit
    -0.07
    ------------
    -0.07
     abstraction
    -0.07
    iner
    -0.07
    iche
    -0.07
    POSITIVE LOGITS
     Inv
    0.20
    incible
    0.18
     INV
    0.18
     inv
    0.17
    .Inv
    0.17
    -inv
    0.17
    TargetException
    0.16
    esco
    0.15
     invitations
    0.15
     invited
    0.15
    Activations Density 0.036%

    No Known Activations