© 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. 90081
    Prev
    Next
    INDEX
    Explanations

    throw, thrown, throwaway

    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
    @stop
    -0.12
    @update
    -0.11
     Grü
    -0.11
    }@
    -0.11
    .@
    -0.10
    Sizes
    -0.10
    Liked
    -0.10
     âĻ¥
    -0.10
     #@
    -0.09
     grac
    -0.09
    POSITIVE LOGITS
     throw
    0.14
    throw
    0.12
    _throw
    0.11
     Throw
    0.11
    dont
    0.10
     thrown
    0.10
     throws
    0.09
    _-_
    0.09
     THROW
    0.09
    --
    0.09
    Activations Density 0.038%

    No Known Activations