© 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. 113553
    Prev
    Next
    INDEX
    Explanations

    enough to

    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
     enough
    -0.30
     Enough
    -0.25
    Enough
    -0.21
    (er
    -0.18
     sufficient
    -0.16
    -en
    -0.13
    è¶
    -0.12
    ongan
    -0.12
    erot
    -0.12
    -ish
    -0.12
    POSITIVE LOGITS
    ilde
    0.08
     warrant
    0.08
     bog
    0.07
     Bog
    0.07
    ths
    0.07
    ido
    0.07
    ijo
    0.07
     merit
    0.06
     stag
    0.06
    528
    0.06
    Activations Density 0.017%

    No Known Activations