© 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. 27390
    Prev
    Next
    INDEX
    Explanations

    hassle free and easy process

    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
    /Product
    -0.11
     richest
    -0.10
     costly
    -0.10
    ouncer
    -0.10
    trainer
    -0.09
     cosplay
    -0.09
     richer
    -0.09
    åŁ
    -0.09
    undos
    -0.09
     ~=
    -0.09
    POSITIVE LOGITS
     hassle
    0.28
     ease
    0.26
     streamlined
    0.26
     convenience
    0.24
     seamless
    0.24
     simplicity
    0.22
     easy
    0.22
     convenient
    0.22
     straightforward
    0.21
     streamline
    0.21
    Activations Density 0.135%

    No Known Activations