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. 27-TRANSCODER-HP
    4. 842
    Prev
    Next
    INDEX
    Explanations

    formal writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĿ¡è¯Ħ论
    -0.24
     ordered
    -0.24
    rena
    -0.24
    ypo
    -0.24
    stable
    -0.23
    .Ordinal
    -0.23
     Axios
    -0.23
     Peninsula
    -0.23
    èħ¿
    -0.23
    AIM
    -0.23
    POSITIVE LOGITS
    ográf
    0.26
    覺
    0.26
    è§ī
    0.26
    quit
    0.25
    å¢ĥçķĮ
    0.25
     Reese
    0.25
    æķ¢
    0.24
     reserved
    0.24
    -after
    0.24
     Nightmare
    0.24
    Activations Density 0.002%

    No Known Activations