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

    quote

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_0.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.0.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odox
    -0.25
    committed
    -0.25
    andum
    -0.25
    æĹ¥åľ¨
    -0.25
    foil
    -0.24
     Presented
    -0.24
    cline
    -0.24
     aired
    -0.24
     ranking
    -0.23
     Clo
    -0.23
    POSITIVE LOGITS
    è¶¾
    0.26
    à¹Ħหว
    0.26
     íķ¨
    0.25
    æ¯į亲
    0.24
     Sebast
    0.24
    åħ¸ç¤¼
    0.24
    人å¿ĥ
    0.23
    -valid
    0.23
    mother
    0.23
    å¾®ç¬ij
    0.23
    Activations Density 3.480%

    No Known Activations