© 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. 116148
    Prev
    Next
    INDEX
    Explanations

    fashion

    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
     HOR
    -0.10
    '?
    -0.10
     disadv
    -0.09
    -ie
    -0.09
     helicopt
    -0.09
    __$
    -0.08
     hott
    -0.08
    (front
    -0.08
     Dont
    -0.08
    ophil
    -0.08
    POSITIVE LOGITS
    âĢ¦but
    0.12
    âĢ¦and
    0.11
    âĢ¦I
    0.10
    ,LOCATION
    0.10
     Voy
    0.10
    ,$
    0.10
    âĢ¦it
    0.10
    âĢ¦the
    0.09
    ,[
    0.09
     bless
    0.09
    Activations Density 0.121%

    No Known Activations