© 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. 24-TRANSCODER-HP
    7. 151436
    Prev
    Next
    INDEX
    Explanations

    Proximity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ogl
    -0.26
    裤
    -0.24
     Tried
    -0.23
    两æĿ¡
    -0.23
     Woj
    -0.23
    prefs
    -0.23
    京津åĨĢ
    -0.23
    éĥ½æĥ³
    -0.23
     JNIEnv
    -0.23
    ught
    -0.22
    POSITIVE LOGITS
     directly
    0.28
    bens
    0.27
    å³Ļ
    0.27
    ä¸Ģ线
    0.26
    itably
    0.25
     overhead
    0.24
    æĵįä½ľ
    0.24
     proximity
    0.24
    completion
    0.24
     closest
    0.24
    Activations Density 0.378%

    No Known Activations