© 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. 5376
    Prev
    Next
    INDEX
    Explanations

    plus or minus

    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
    å·²ä¹ħ
    -0.27
    åħ·ä½ĵæĥħåĨµ
    -0.26
     contemplated
    -0.26
    )|(
    -0.26
    bage
    -0.26
     TestCase
    -0.25
    rong
    -0.25
    ponder
    -0.24
    åıijå±ķ模å¼ı
    -0.24
    åı¯èĥ½åıijçĶŁ
    -0.24
    POSITIVE LOGITS
     har
    0.27
     PRIV
    0.25
    æĬ±æŃī
    0.25
    miner
    0.24
    çļĦå°ı
    0.24
    onet
    0.24
    交代
    0.24
    andan
    0.24
    çĪ½
    0.24
    mint
    0.23
    Activations Density 0.003%

    No Known Activations