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. 23-TRANSCODER-HP
    4. 15110
    Prev
    Next
    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĭŃ
    -0.26
     qw
    -0.25
    staff
    -0.25
    æŃĮåͱ
    -0.25
    step
    -0.24
    forget
    -0.24
     egret
    -0.24
    课
    -0.24
    æ¸ħæī«
    -0.24
    .getContentPane
    -0.24
    POSITIVE LOGITS
     ancestral
    0.28
    år
    0.27
     Mount
    0.25
    åī©ä½Ļ
    0.24
    erator
    0.24
    WithValue
    0.24
    æī©å®¹
    0.24
    riere
    0.24
    kö
    0.23
    resco
    0.23
    Activations Density 0.005%

    No Known Activations