© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5014
    Prev
    Next
    INDEX
    Explanations

    common English words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erna
    -0.28
    å®¶ä½ı
    -0.26
    äºĴéĢļ
    -0.26
     вÑģÑĤÑĢеÑĩа
    -0.25
    çĶŁæĢģä¿ĿæĬ¤
    -0.25
    peria
    -0.25
    Binary
    -0.25
    istan
    -0.25
    åī©ä¸ĭçļĦ
    -0.24
    家人
    -0.23
    POSITIVE LOGITS
    æ¶¡
    0.30
    .imgur
    0.28
    èĨ½
    0.27
    æĴķ
    0.26
     bif
    0.26
    åĵįåºĶ
    0.26
    occo
    0.25
    PG
    0.25
    DEL
    0.25
    çĥ
    0.24
    Activations Density 3.463%

    No Known Activations