© 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. 5021
    Prev
    Next
    INDEX
    Explanations

    elongated shapes, narrow, pointed

    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
     blanket
    -0.10
    sizes
    -0.10
    osen
    -0.10
     Satisfaction
    -0.09
     plates
    -0.09
    SID
    -0.09
     Kor
    -0.09
    overs
    -0.09
     Tyson
    -0.09
     Short
    -0.09
    POSITIVE LOGITS
     elong
    0.18
     penetrating
    0.17
     narrow
    0.17
     penetr
    0.16
     slender
    0.15
     narrower
    0.15
     penetration
    0.15
     Narrow
    0.15
     piercing
    0.15
     penetrate
    0.15
    Activations Density 0.340%

    No Known Activations