© 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. 97862
    Prev
    Next
    INDEX
    Explanations

    Code, design, technical documentation

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Human
    -0.31
    å¢Ļä¸Ĭ
    -0.28
    è±ģ
    -0.26
    æŃ£å½ĵ
    -0.26
    æŁIJä¸Ģ
    -0.25
    éĺµ
    -0.25
    å¢ĻéĿ¢
    -0.25
    atically
    -0.24
    wall
    -0.24
    æĥħåĨµä¸ĭ
    -0.24
    POSITIVE LOGITS
    orns
    0.27
    oste
    0.27
    ourage
    0.27
    vide
    0.25
    ÑĤиÑĢов
    0.25
    oref
    0.25
     Paypal
    0.24
    iface
    0.24
    -figure
    0.24
    æ°¤
    0.24
    Activations Density 0.028%

    No Known Activations