© 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. 112086
    Prev
    Next
    INDEX
    Explanations

    Len followed by names or suffixes

    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
    IMP
    -0.09
     imp
    -0.08
     irgend
    -0.07
     att
    -0.07
    uren
    -0.07
     imperson
    -0.07
    uele
    -0.07
    imp
    -0.07
    break
    -0.06
    à¸Ĭ
    -0.06
    POSITIVE LOGITS
    nox
    0.18
    ient
    0.17
    ovo
    0.13
    ngth
    0.12
    otre
    0.11
    ox
    0.11
    /posts
    0.11
    aign
    0.11
    adro
    0.11
    IENT
    0.11
    Activations Density 0.042%

    No Known Activations