© 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. 114461
    Prev
    Next
    INDEX
    Explanations

    vr headset, God honoring, teleph, Sydenham

    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
    burgh
    -0.10
     incr
    -0.09
     prolong
    -0.09
     Nero
    -0.09
     disposition
    -0.09
     intox
    -0.08
     Zap
    -0.08
     tremend
    -0.08
     dispos
    -0.08
     Martin
    -0.08
    POSITIVE LOGITS
    łéĻ¤
    0.11
    cip
    0.09
    uard
    0.09
    gent
    0.09
    ¾ç¤º
    0.09
    sic
    0.08
    osti
    0.08
    /ws
    0.08
    Spr
    0.08
     (“
    0.08
    Activations Density 0.081%

    No Known Activations