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. 53224
    Prev
    Next
    INDEX
    Explanations

    even

    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
    èĵĸ
    -0.27
     Dion
    -0.26
    /static
    -0.25
    æ¿ij
    -0.25
     report
    -0.24
     Horn
    -0.24
    orsi
    -0.24
    ernal
    -0.24
     plus
    -0.24
    راÙħ
    -0.24
    POSITIVE LOGITS
    èĥľ
    0.28
    ovo
    0.28
     outr
    0.26
    aire
    0.26
    éĤ£è¾¹
    0.25
    å·į
    0.25
     Strip
    0.25
    åı£åı·
    0.25
     Moff
    0.25
    anth
    0.25
    Activations Density 0.002%

    No Known Activations