© 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. 48034
    Prev
    Next
    INDEX
    Explanations

    hop followed by specific words

    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
    ation
    -0.11
    yer
    -0.11
    uality
    -0.11
    tlement
    -0.11
    ERRU
    -0.11
    ONE
    -0.10
     domin
    -0.10
     refute
    -0.10
    cmb
    -0.09
    ités
    -0.09
    POSITIVE LOGITS
    otts
    0.09
    inka
    0.08
     Transcript
    0.08
     indirect
    0.08
     Kore
    0.08
     inward
    0.08
     brute
    0.07
    <<<<<<<
    0.07
     Ober
    0.07
     tastes
    0.07
    Activations Density 0.012%

    No Known Activations