© 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. 5903
    Prev
    Next
    INDEX
    Explanations

    scientific research

    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
    éģĩ
    -0.35
    alice
    -0.28
    åıĪ好
    -0.27
    ãĥ¼ãĤ¿
    -0.26
    ynamo
    -0.26
    rys
    -0.26
    erals
    -0.25
    enders
    -0.25
    身ä½ĵåģ¥åº·
    -0.25
    天çĦ¶
    -0.25
    POSITIVE LOGITS
    бÑĥÑĢ
    0.33
    KG
    0.28
    .onNext
    0.26
    Åľ
    0.23
    DJ
    0.23
     KG
    0.23
    ">#
    0.23
    为客æĪ·
    0.23
    çIJ¬
    0.23
    ÙħرÙĥ
    0.23
    Activations Density 0.841%

    No Known Activations