© 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. 130081
    Prev
    Next
    INDEX
    Explanations

    and

    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
    anya
    -0.29
    缴
    -0.28
    /Gate
    -0.26
    Person
    -0.26
    ãģĹãģ°
    -0.25
    omatic
    -0.24
    anything
    -0.24
    Grey
    -0.24
    æĪijè¿ĺ
    -0.24
    inally
    -0.24
    POSITIVE LOGITS
    ä¸įæĥ³
    0.33
    æĥ³è¦ģ
    0.32
    ãģ©ãģĨãģĹãģ¦ãĤĤ
    0.30
    ä¸įæĸ¹ä¾¿
    0.30
     wish
    0.29
     want
    0.28
    ertools
    0.27
    æĥ³æī¾
    0.27
    authenticated
    0.27
    äºŁ
    0.27
    Activations Density 0.011%

    No Known Activations