© 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. 33148
    Prev
    Next
    INDEX
    Explanations

    attached to or connected

    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
    arin
    -0.11
    .jasper
    -0.11
    onest
    -0.10
     accompanied
    -0.10
     foreground
    -0.10
     dressed
    -0.10
     overwhel
    -0.10
     Raven
    -0.10
     linger
    -0.10
    enor
    -0.10
    POSITIVE LOGITS
     attach
    0.23
     tie
    0.21
     connect
    0.20
     attaching
    0.19
     attachment
    0.19
     attaches
    0.19
     anchor
    0.18
     tied
    0.18
     connects
    0.18
     tying
    0.18
    Activations Density 0.295%

    No Known Activations