© 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. 15104
    Prev
    Next
    INDEX
    Explanations

    good followed by adjective

    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
    /md
    -0.10
     Fuse
    -0.09
     purely
    -0.09
    onga
    -0.09
     ceased
    -0.08
     Tam
    -0.08
    anth
    -0.08
     meetings
    -0.08
    idon
    -0.08
     Ce
    -0.07
    POSITIVE LOGITS
     amount
    0.16
     amounts
    0.15
     Amount
    0.13
     Samar
    0.12
     observation
    0.11
    luck
    0.11
    amount
    0.11
    Amount
    0.11
     Timing
    0.11
     Observation
    0.10
    Activations Density 0.062%

    No Known Activations