© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1125-32B
    5. 32-RES-BATCHTOPK-131K
    7. 90557
    Prev
    Next
    INDEX
    Explanations

    requires submission

    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
    umpt
    -0.11
     descr
    -0.10
    omm
    -0.10
    opup
    -0.10
    enn
    -0.10
    ogl
    -0.10
     Whisper
    -0.10
    hem
    -0.09
     colle
    -0.09
    uzz
    -0.09
    POSITIVE LOGITS
     requires
    0.34
     must
    0.30
     Requires
    0.25
    requires
    0.25
    must
    0.24
    å¿ħ
    0.23
    Requires
    0.23
     require
    0.23
     necess
    0.22
     MUST
    0.21
    Activations Density 0.435%

    No Known Activations