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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163358
    Prev
    Next
    INDEX
    Explanations

    zero

    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
    cour
    -0.27
     JObject
    -0.26
    celain
    -0.25
    vod
    -0.25
    åĨĴåĩº
    -0.24
     aggress
    -0.23
    çĸ¾
    -0.23
    erged
    -0.23
    Serialize
    -0.23
    é«ĺä½İ
    -0.22
    POSITIVE LOGITS
    Touches
    0.28
    ĭè¯ķ
    0.28
    ï¿£
    0.26
    æıIJä¾ĽçļĦ
    0.24
    è¯ķåį·
    0.24
    çĭĻ
    0.24
    ä¸į对
    0.23
    æĹ¢åı¯ä»¥
    0.23
     dow
    0.23
    åĪ«çļĦ
    0.23
    Activations Density 0.007%

    No Known Activations