© 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. 7798
    Prev
    Next
    INDEX
    Explanations

    taken into account

    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
     fuss
    -0.10
    çĶ
    -0.09
    609
    -0.09
     scop
    -0.09
     Mae
    -0.09
     flop
    -0.08
     modest
    -0.08
     HT
    -0.08
     bomb
    -0.08
     consensus
    -0.08
    POSITIVE LOGITS
     destiny
    0.13
     autop
    0.10
     Destiny
    0.10
     impatient
    0.10
    control
    0.10
    indi
    0.10
     hands
    0.10
    -self
    0.10
     DIY
    0.10
     control
    0.10
    Activations Density 0.003%

    No Known Activations