© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 113781
    Prev
    Next
    INDEX
    Explanations

    find specific information

    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
     attentive
    -0.10
    wk
    -0.10
    ollah
    -0.09
    kh
    -0.09
     Gad
    -0.09
     slate
    -0.09
     Hick
    -0.09
    umpt
    -0.09
    768
    -0.09
    ré
    -0.09
    POSITIVE LOGITS
     specific
    0.24
     particular
    0.18
     Specific
    0.18
     desired
    0.18
    Specific
    0.16
    specific
    0.15
     quickly
    0.15
     searched
    0.14
     relevant
    0.14
    _specific
    0.14
    Activations Density 0.172%

    No Known Activations