© 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. 49910
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     prow
    -0.10
    adel
    -0.09
     slip
    -0.09
     Raum
    -0.09
     sip
    -0.09
    atra
    -0.09
     jab
    -0.09
     lapse
    -0.08
     tendency
    -0.08
     Foo
    -0.08
    POSITIVE LOGITS
     Cah
    0.09
    umph
    0.09
    halt
    0.09
     lum
    0.09
     transl
    0.09
     controvers
    0.08
     Ske
    0.08
    osal
    0.08
     affirm
    0.08
    .fr
    0.08
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.