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. 24255
    Prev
    Next
    INDEX
    Explanations

    nearest

    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
    edith
    -0.25
    .wik
    -0.24
    IMPORTANT
    -0.24
     Introduced
    -0.24
    ä¹°åħ¥
    -0.23
     Acid
    -0.23
    Spec
    -0.23
     ACCEPT
    -0.23
    ARTH
    -0.23
    chie
    -0.23
    POSITIVE LOGITS
    æ¹¾
    0.29
     bent
    0.28
    å®¶åĬ¡
    0.27
    å±Ī
    0.26
    ictionary
    0.26
    è¡Ĺ头
    0.25
    çĺ«
    0.25
     flakes
    0.24
    å¾Ĺèµ·
    0.24
    ausal
    0.24
    Activations Density 0.003%

    No Known Activations