© 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. 26744
    Prev
    Next
    INDEX
    Explanations

    boundary or completion

    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
    illard
    -0.13
     besonders
    -0.12
     indefinitely
    -0.12
    akis
    -0.12
     jusqu
    -0.12
     starting
    -0.11
    ente
    -0.10
    ien
    -0.10
    itesse
    -0.10
    pf
    -0.10
    POSITIVE LOGITS
     somewhere
    0.18
     at
    0.16
     abruptly
    0.13
     near
    0.12
     midway
    0.12
     sooner
    0.11
     halfway
    0.11
     around
    0.10
     below
    0.10
    	at
    0.09
    Activations Density 0.055%

    No Known Activations