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. 1304
    Prev
    Next
    INDEX
    Explanations

    beef

    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
    quent
    -0.27
    å¼Ģ端
    -0.26
    nds
    -0.26
    unds
    -0.25
    eor
    -0.24
    常è§Ħ
    -0.24
    å·®åĪ«
    -0.24
     Unt
    -0.24
    NotificationCenter
    -0.23
    nown
    -0.23
    POSITIVE LOGITS
    _wf
    0.33
    ulin
    0.28
    hf
    0.27
    ht
    0.26
    WF
    0.26
    wf
    0.26
    å¦ĤæŀľæĤ¨
    0.25
    wig
    0.25
    hp
    0.24
    scription
    0.24
    Activations Density 0.786%

    No Known Activations