© 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. 4453
    Prev
    Next
    INDEX
    Explanations

    five represent

    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
    akra
    -0.10
    541
    -0.10
     Malk
    -0.10
    527
    -0.09
    sg
    -0.09
     Willis
    -0.09
    zp
    -0.09
    移åĪ°
    -0.09
    MT
    -0.09
     AG
    -0.08
    POSITIVE LOGITS
     the
    0.17
     their
    0.15
     those
    0.14
     its
    0.13
     your
    0.12
    alue
    0.12
    those
    0.11
    _the
    0.11
     our
    0.10
     oneself
    0.10
    Activations Density 0.321%

    No Known Activations