© 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. 19-TRANSCODER-HP
    7. 5931
    Prev
    Next
    INDEX
    Explanations

    Internet and websites

    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
     stubborn
    -0.26
    aily
    -0.25
    obe
    -0.25
    å¼ĢäºĨ
    -0.25
    deb
    -0.25
    asin
    -0.24
     converge
    -0.24
    ographer
    -0.24
    iates
    -0.24
    个人è§ĤçĤ¹
    -0.24
    POSITIVE LOGITS
    æ±ł
    0.24
     thơ
    0.24
    篷
    0.24
    .Merge
    0.24
    ä¸ĢèĦļ
    0.24
    laws
    0.24
    ancements
    0.23
    #================================================================
    0.23
    .Pool
    0.23
    urst
    0.23
    Activations Density 0.004%

    No Known Activations