© 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. 88529
    Prev
    Next
    INDEX
    Explanations

    Mixed content/instructions

    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
    åĩºäºİ
    -0.27
    å½ĵå¹´
    -0.27
     formation
    -0.26
     believed
    -0.25
    èĩ³æĸ¼
    -0.25
    è¾ķ
    -0.24
    thumb
    -0.24
     Prä
    -0.24
    鹬
    -0.24
    elihood
    -0.23
    POSITIVE LOGITS
    æŁ¥çľĭæĽ´å¤ļ
    0.26
    mó
    0.26
    æĻļ
    0.26
    åĮħ容
    0.26
     SEC
    0.24
    _FM
    0.24
     recommends
    0.23
    cce
    0.23
    ç§Ĵ
    0.23
    alen
    0.23
    Activations Density 0.023%

    No Known Activations