© 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. 30038
    Prev
    Next
    INDEX
    Explanations

    valley or gorge features

    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
    anye
    -0.11
     hyperlink
    -0.11
     blur
    -0.11
     verbosity
    -0.11
    zure
    -0.10
     reused
    -0.10
     Regions
    -0.10
     decor
    -0.10
     conj
    -0.10
     disclaimer
    -0.10
    POSITIVE LOGITS
     valley
    0.24
     canyon
    0.19
     Valley
    0.16
     bowl
    0.15
     valleys
    0.14
     trapped
    0.13
     funnel
    0.13
     gorge
    0.13
     narrow
    0.13
     basin
    0.13
    Activations Density 0.359%

    No Known Activations