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. 24154
    Prev
    Next
    INDEX
    Explanations

    witchcraft and homesteading

    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
    icle
    -0.27
    sn
    -0.27
    inery
    -0.27
    tern
    -0.26
    atic
    -0.26
    fly
    -0.26
     ipad
    -0.25
    äººæł¼
    -0.24
    两åIJį
    -0.24
    管çIJĨåijĺ
    -0.24
    POSITIVE LOGITS
    ä¸į说
    0.30
    å¤Ń
    0.27
    èĭ´
    0.26
    è«®
    0.25
     remin
    0.24
    ;top
    0.24
    èĢĮä¸į
    0.24
    èĢĮåIJİ
    0.23
    èĢĮ导èĩ´
    0.23
     carpets
    0.23
    Activations Density 0.001%

    No Known Activations