© 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. 112167
    Prev
    Next
    INDEX
    Explanations

    stopped me in my tracks

    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
    .IsNullOr
    -0.09
    fty
    -0.08
    ryn
    -0.08
    fsp
    -0.08
     Pul
    -0.08
    toi
    -0.08
     Lei
    -0.08
     Barnett
    -0.08
     FRE
    -0.08
    _fence
    -0.08
    POSITIVE LOGITS
     tracks
    0.38
     Tracks
    0.31
    Tracks
    0.26
    tracks
    0.24
     track
    0.21
    _tracks
    0.18
     TRACK
    0.18
    track
    0.17
    Track
    0.17
    -track
    0.16
    Activations Density 0.065%

    No Known Activations