© 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. 5776
    Prev
    Next
    INDEX
    Explanations

    articles/essays

    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
    lements
    -0.29
    imat
    -0.27
    INU
    -0.25
     Downloads
    -0.25
    @student
    -0.24
    æĶ¾å¿ĥ
    -0.24
    ancements
    -0.24
    inia
    -0.24
    _resume
    -0.24
     upscale
    -0.23
    POSITIVE LOGITS
    åħ¬ç¤º
    0.33
    è¯ģæĺİ
    0.28
    æĪ³
    0.27
    itled
    0.26
    表çİ°
    0.26
    纪
    0.26
    绣ä¸Ģ
    0.25
    æŶåĪ»
    0.25
    s
    0.25
    goo
    0.25
    Activations Density 0.008%

    No Known Activations