© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 98793
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mac
    -0.30
     bern
    -0.27
     act
    -0.26
    bern
    -0.26
     Act
    -0.26
     Av
    -0.26
    geb
    -0.25
    act
    -0.25
     perman
    -0.25
     Arbit
    -0.24
    POSITIVE LOGITS
     >",
    0.31
     disproportion
    0.31
    $",
    0.27
    Ļ¶
    0.27
    å°ıé¾Ļ
    0.27
     =",
    0.27
    ä¸įæŃ»
    0.27
    accessible
    0.25
    -",
    0.25
    çݩ家们
    0.25
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.