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. 11-TRANSCODER-HP
    4. 46783
    Prev
    Next
    INDEX
    Explanations

    When

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_11.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.11.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undi
    -0.29
    heck
    -0.28
    ogl
    -0.28
    åij½
    -0.26
     interact
    -0.25
     slides
    -0.25
    åī¯
    -0.25
     stub
    -0.24
     c
    -0.24
    åij½é¢ĺ
    -0.24
    POSITIVE LOGITS
     Personality
    0.27
    .lin
    0.26
    imenti
    0.26
    ospace
    0.25
     VOL
    0.25
    被æī§è¡Į
    0.25
     Rut
    0.24
    äºĮ人
    0.24
    Vm
    0.24
    ä¸Ģ家人
    0.24
    Activations Density 0.021%

    No Known Activations