© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7519
    Prev
    Next
    INDEX
    Explanations

    Positive experiences and rewards

    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
    oom
    -0.27
    屦
    -0.27
    å¡ŀ
    -0.25
    æ¯ıä¸Ģ个人
    -0.25
    èĥ½ä¸įèĥ½
    -0.25
    .unknown
    -0.24
    æĬ±æĢ¨
    -0.24
    æ±²
    -0.24
    åį·
    -0.24
    çľĭä¸įæĩĤ
    -0.24
    POSITIVE LOGITS
    æĪIJå°±æĦŁ
    0.48
     rewarding
    0.40
    èĥľåĪ©
    0.36
     rewards
    0.35
     Reward
    0.35
     reward
    0.34
    èİ·èĥľ
    0.34
    Reward
    0.34
     victory
    0.33
     rewarded
    0.33
    Activations Density 0.062%

    No Known Activations