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. 97998
    Prev
    Next
    INDEX
    Explanations

    Published

    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
     Atkins
    -0.26
    å°Ķ
    -0.26
     createState
    -0.25
    åĴ¸
    -0.25
     salv
    -0.25
    -ing
    -0.24
    建设åĴĮ
    -0.24
     cooker
    -0.24
    hei
    -0.24
    ISTIC
    -0.24
    POSITIVE LOGITS
    æĹ¥ä¸ĭåįĪ
    0.28
     rupture
    0.26
    çİij
    0.26
    æ°Ķ
    0.26
     nied
    0.26
    bubble
    0.25
    bull
    0.25
    iform
    0.25
    çł´è£Ĥ
    0.25
     ripple
    0.25
    Activations Density 0.003%

    No Known Activations