© 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. 112544
    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
    åı¦ä¸Ģ
    -0.31
    éĩįå¤§é¡¹çĽ®
    -0.27
    åı¦ä¸Ģ个
    -0.26
    Another
    -0.26
     another
    -0.26
    对åºĶçļĦ
    -0.25
    éĩį大
    -0.24
    ahi
    -0.24
     Another
    -0.24
    åįķ
    -0.24
    POSITIVE LOGITS
    @↵↵
    0.31
    oping
    0.29
    ))}↵
    0.26
    ?)↵↵
    0.25
    ÙħÙĪÙĦ
    0.24
    交代
    0.24
    ðŁĺĦ
    0.24
    ç»
    0.23
    @c
    0.23
     Kata
    0.23
    Activations Density 0.005%

    No Known Activations