© 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. 5874
    Prev
    Next
    INDEX
    Explanations

    Code and queries

    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
    ERGE
    -0.28
    ÄIJT
    -0.26
    GES
    -0.24
    -ended
    -0.24
    apanese
    -0.23
     smoother
    -0.23
    å±ĭ
    -0.23
    пÑĢоÑģ
    -0.23
    GER
    -0.23
    _nt
    -0.23
    POSITIVE LOGITS
    ä¸Ģ个个
    0.27
    伤害
    0.24
    åħ³
    0.24
     exhaust
    0.23
    ç»ĵ
    0.23
    awns
    0.23
    大家
    0.23
    _interrupt
    0.23
    æľī个
    0.23
    ÙģÙĦ
    0.23
    Activations Density 0.006%

    No Known Activations