© 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. 52567
    Prev
    Next
    INDEX
    Explanations

    in

    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
    IZED
    -0.25
    åĮº
    -0.24
    ities
    -0.24
    IDAD
    -0.24
    	cc
    -0.23
    izedName
    -0.23
    衽
    -0.23
    âĹĦ
    -0.23
     trắng
    -0.23
     Outputs
    -0.23
    POSITIVE LOGITS
    åĸľ
    0.29
    as
    0.28
     success
    0.27
     twist
    0.27
    \n
    0.26
    ARI
    0.25
    ognition
    0.24
     Suns
    0.24
    ä¸Ģå¾ĭ
    0.24
     wish
    0.24
    Activations Density 0.009%

    No Known Activations