© 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. 113700
    Prev
    Next
    INDEX
    Explanations

    another

    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
     Rein
    -0.10
    ););↵
    -0.09
    "\↵
    -0.08
    (Arg
    -0.08
    eger
    -0.08
    olist
    -0.08
    wb
    -0.08
    +'
    -0.08
    istrate
    -0.08
    ,");↵
    -0.08
    POSITIVE LOGITS
    !
    0.14
     followed
    0.14
    :
    0.14
     ensued
    0.13
     came
    0.12
    !:
    0.11
     follows
    0.11
     suff
    0.11
     accompanies
    0.10
     Pause
    0.10
    Activations Density 0.084%

    No Known Activations