© 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. 115985
    Prev
    Next
    INDEX
    Explanations

    am followed by a name

    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
    mie
    -0.11
    i
    -0.10
    iets
    -0.10
    де
    -0.10
    aan
    -0.09
     basis
    -0.09
    aad
    -0.09
    aida
    -0.09
     pred
    -0.09
    acom
    -0.09
    POSITIVE LOGITS
    ycin
    0.13
    sterdam
    0.12
     Provid
    0.10
    ateur
    0.10
    anager
    0.09
    param
    0.09
    alles
    0.09
    rk
    0.09
     gia
    0.09
    ouse
    0.09
    Activations Density 0.086%

    No Known Activations