© 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. 116520
    Prev
    Next
    INDEX
    Explanations

    tur followed by suffixes

    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
    cth
    -0.10
    essed
    -0.09
    ured
    -0.09
    alice
    -0.09
    bard
    -0.09
    rail
    -0.09
    iert
    -0.09
    oured
    -0.09
    alis
    -0.09
    ency
    -0.09
    POSITIVE LOGITS
    lund
    0.10
     sheer
    0.10
    s
    0.10
    icens
    0.09
    rones
    0.09
    ismo
    0.09
    ishes
    0.09
    opup
    0.08
    vey
    0.08
    çķª
    0.08
    Activations Density 0.016%

    No Known Activations