© 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. 115486
    Prev
    Next
    INDEX
    Explanations

    part or partly

    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
    äh
    -0.08
    odos
    -0.08
    ader
    -0.08
    .Framework
    -0.08
     oppos
    -0.08
    oman
    -0.08
    rieve
    -0.07
    olan
    -0.07
     opposite
    -0.07
    iken
    -0.07
    POSITIVE LOGITS
     partly
    0.22
     part
    0.21
     partially
    0.17
    éĥ¨
    0.15
     PART
    0.15
    /part
    0.15
     Part
    0.14
     half
    0.14
    part
    0.14
     mostly
    0.13
    Activations Density 0.118%

    No Known Activations