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. 27-TRANSCODER-HP
    4. 976
    Prev
    Next
    INDEX
    Explanations

    code, legal, academic text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scientific
    -0.34
    ç§ijçłĶ
    -0.28
    ç§ijåѦçłĶç©¶
    -0.28
     Institutes
    -0.28
    è¯ļ
    -0.27
    scient
    -0.27
     institutes
    -0.26
    çłĶ究人åijĺ
    -0.26
    ç§ij
    -0.26
    ammers
    -0.25
    POSITIVE LOGITS
     appellate
    0.32
     chiếu
    0.28
    dda
    0.27
     graduation
    0.26
    æį»
    0.25
    åĴ«
    0.25
    ç°½
    0.25
    .setResult
    0.24
    çѾ
    0.24
     hang
    0.24
    Activations Density 0.002%

    No Known Activations