© 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. 33-TRANSCODER-HP
    7. 54824
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    astos
    -0.28
    /screen
    -0.27
    enta
    -0.27
    oreach
    -0.27
    	mat
    -0.25
    è£ģå®ļ
    -0.25
    å¼Ģ车
    -0.25
    oste
    -0.25
    糯
    -0.25
    Toggle
    -0.25
    POSITIVE LOGITS
     PR
    0.26
    å¿Ĺ
    0.26
     South
    0.26
     pot
    0.26
    Pot
    0.26
    ä¼ij
    0.26
    _scheme
    0.26
    .Mouse
    0.25
    PR
    0.25
    SC
    0.25
    Activations Density 0.010%

    No Known Activations