© 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
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161693
    Prev
    Next
    INDEX
    Explanations

    make

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -Fi
    -0.25
    就没æľī
    -0.25
    å¹²äºĭ
    -0.25
    -height
    -0.24
    页
    -0.24
     early
    -0.23
    åĩıæİĴ
    -0.23
     short
    -0.23
    æĽ´æľī
    -0.23
    çľĭä¸įåĪ°
    -0.23
    POSITIVE LOGITS
    å®ĥ
    0.33
    对åħ¶è¿Ľè¡Į
    0.31
     them
    0.30
    å®ĥçļĦ
    0.29
    æĬĬå®ĥ
    0.28
    使ä¹ĭ
    0.28
    使åħ¶
    0.26
    å®ĥ们
    0.26
    everything
    0.26
    è¿Ļ家åħ¬åı¸
    0.25
    Activations Density 0.007%

    No Known Activations