© 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. 115844
    Prev
    Next
    INDEX
    Explanations

    parts of 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
     Chad
    -0.11
     tide
    -0.10
    fly
    -0.09
     Kami
    -0.09
     Carey
    -0.09
     Min
    -0.09
    semi
    -0.09
     cri
    -0.09
    caster
    -0.09
     poss
    -0.09
    POSITIVE LOGITS
     brace
    0.09
     anyhow
    0.09
    ché
    0.08
    yles
    0.08
    dorf
    0.08
     esk
    0.08
     enfer
    0.08
     tow
    0.08
    aise
    0.08
    enez
    0.08
    Activations Density 0.001%

    No Known Activations