Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 7-TRANSCODER-HP
    4. 15492
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_7.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.7.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¶Ł
    -0.27
    alic
    -0.26
    æĹłå¿§
    -0.26
     alma
    -0.26
    ä»İèĢĮ
    -0.25
    å¡«
    -0.25
     summary
    -0.25
    cano
    -0.24
    uary
    -0.24
    entions
    -0.24
    POSITIVE LOGITS
    ini
    0.28
    hil
    0.26
    /player
    0.26
     Morton
    0.24
     Phát
    0.24
     dimensions
    0.24
    olin
    0.23
    ONGL
    0.23
    å¤ļ人
    0.23
    -income
    0.23
    Activations Density 0.000%

    No Known Activations