© 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. 91869
    Prev
    Next
    INDEX
    Explanations

    holding something in place

    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
    agate
    -0.11
     outright
    -0.10
    PTY
    -0.10
    (cont
    -0.10
    ç±
    -0.10
     pal
    -0.09
    esser
    -0.09
    egl
    -0.09
    lin
    -0.09
     allo
    -0.09
    POSITIVE LOGITS
     atop
    0.12
    ment
    0.11
    anka
    0.10
    ments
    0.09
    alis
    0.09
    ynth
    0.09
    kus
    0.09
    EMENT
    0.09
    hind
    0.09
    unt
    0.08
    Activations Density 0.011%

    No Known Activations