© 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. 163303
    Prev
    Next
    INDEX
    Explanations

    the

    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
    dump
    -0.27
     dus
    -0.26
    .LoggerFactory
    -0.25
     elapsed
    -0.25
     lòng
    -0.25
    èĩ¾
    -0.25
     imply
    -0.24
    è¿ĩåī©
    -0.24
     minut
    -0.24
    ç»Ī端
    -0.24
    POSITIVE LOGITS
    бил
    0.26
     strategy
    0.26
    åĴ¸
    0.26
    른
    0.25
     strategies
    0.24
     OPTIONAL
    0.24
    çŀ¿
    0.24
    åħĪè¿Ľ
    0.24
    çŃĸçķ¥
    0.23
    eks
    0.23
    Activations Density 0.005%

    No Known Activations