© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 35-TRANSCODER-HP
    7. 40589
    Prev
    Next
    INDEX
    Explanations

    moral

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     the
    -0.35
     a
    -0.33
     Ned
    -0.26
     ÐijолÑĮ
    -0.26
    tör
    -0.25
    ocked
    -0.24
    	AT
    -0.24
     Bowl
    -0.24
    æ³¼
    -0.23
     Hollow
    -0.23
    POSITIVE LOGITS
     pretext
    0.32
     endorsement
    0.30
     accusation
    0.29
    -abortion
    0.29
     beginnings
    0.29
    -process
    0.29
     obsess
    0.28
     clums
    0.28
     inscription
    0.28
     guise
    0.28
    Activations Density 0.147%

    No Known Activations