© 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. 22-TRANSCODER-HP
    7. 129068
    Prev
    Next
    INDEX
    Explanations

    Methods

    np_max-act · gemini-2.0-flash
    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
    Negative Logits
    enic
    -0.29
    好å¥ĩå¿ĥ
    -0.25
    åIJ¸
    -0.24
    ersed
    -0.24
    xm
    -0.23
    ervoir
    -0.23
    MemoryWarning
    -0.23
    HX
    -0.22
    DOMNode
    -0.22
    qu
    -0.22
    POSITIVE LOGITS
    sing
    0.29
    ?).
    0.27
    ä»ĵ
    0.26
    ?)↵
    0.24
    -earth
    0.24
    å¾Ģä¸ĭ
    0.24
    ourke
    0.24
    çĿ£
    0.24
     оÑĦ
    0.24
    åij½
    0.23
    Activations Density 0.010%

    No Known Activations