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. 2-TRANSCODER-HP
    4. 102
    Prev
    Next
    INDEX
    Explanations

    antidepressant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_2.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.2.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SIDE
    -0.25
    ussian
    -0.25
    @admin
    -0.25
    acl
    -0.24
    pher
    -0.24
    æ¿Ĥ
    -0.24
    ties
    -0.23
    ale
    -0.23
    ipv
    -0.23
     Hast
    -0.23
    POSITIVE LOGITS
    ма
    0.28
    ChartData
    0.26
     sank
    0.25
    å·¥ä½ľæķĪçİĩ
    0.25
    å¥
    0.24
     Panels
    0.24
    inea
    0.24
    举
    0.24
    PageRoute
    0.24
     swim
    0.23
    Activations Density 49.651%

    No Known Activations