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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 41280
    Prev
    Next
    INDEX
    Explanations

    code/text snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å©Ĩ
    -0.26
    -engine
    -0.26
    è¿ijäºĽ
    -0.26
    /engine
    -0.24
     RESPONSE
    -0.24
    ilo
    -0.24
    /response
    -0.24
    ä½ĵæ£Ģ
    -0.24
    éĩįè§Ĩ
    -0.23
    à¸ĸ
    -0.23
    POSITIVE LOGITS
     grou
    0.27
    ter
    0.26
    uzzer
    0.26
     rack
    0.24
    æ°¸
    0.24
    æĪIJåijĺåĽ½
    0.24
    ãģ¹ãģį
    0.24
    社ä¼ļåıijå±ķ
    0.24
     legalization
    0.24
    ä»ħ代表
    0.24
    Activations Density 0.953%

    No Known Activations