© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6059
    Prev
    Next
    INDEX
    Explanations

    bacteria

    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
    åħ¶æīĢ
    -0.26
    mate
    -0.26
    -alist
    -0.25
    [value
    -0.25
    ä»Ĭ
    -0.24
    dv
    -0.24
    æĺĨ
    -0.24
    ç´ĭ
    -0.24
    -org
    -0.23
    è¿Ļéĥ¨åĪĨ
    -0.23
    POSITIVE LOGITS
    luet
    0.27
    ÑĨи
    0.26
    /Instruction
    0.25
    éĢļçĶ¨
    0.24
    archy
    0.24
    ä¸Ĭåİ»
    0.24
    è°ģéĥ½
    0.24
    çľĭå¾Ĺ
    0.24
    PING
    0.23
     Overflow
    0.23
    Activations Density 0.018%

    No Known Activations