© 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. 5299
    Prev
    Next
    INDEX
    Explanations

    exclude

    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
    åºĵéĩĮ
    -0.26
    copies
    -0.25
     dÆ°
    -0.23
    æ¾ľ
    -0.23
     compliments
    -0.22
     Flam
    -0.22
    åIJ¦åĪĻ
    -0.22
    hea
    -0.22
    ugas
    -0.22
    modulo
    -0.22
    POSITIVE LOGITS
    bies
    0.31
    ÃŃch
    0.26
    离å¼Ģ
    0.25
    pping
    0.25
    æĵ¿
    0.24
    IVE
    0.24
    rg
    0.24
    asp
    0.23
    licht
    0.23
    ntity
    0.23
    Activations Density 1.654%

    No Known Activations