© 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. 5255
    Prev
    Next
    INDEX
    Explanations

    subject

    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
    æ±ī
    -0.26
    å°¹
    -0.26
    otland
    -0.24
    official
    -0.23
    counter
    -0.23
    æĪ²
    -0.22
    renc
    -0.22
    éĶµ
    -0.22
    Deg
    -0.22
    èµ·æĿ¥
    -0.22
    POSITIVE LOGITS
    .appspot
    0.26
    ity
    0.25
    ¯¯
    0.24
    tá
    0.23
    -than
    0.23
    ç¥
    0.23
    VML
    0.23
    дÑĥ
    0.23
     matter
    0.23
     appropriate
    0.23
    Activations Density 2.097%

    No Known Activations