Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5659
    Prev
    Next
    INDEX
    Explanations

    technical requests/requirements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quist
    -0.32
     goal
    -0.30
    çļĦ缮æłĩ
    -0.28
    缮æłĩ
    -0.27
     Goal
    -0.26
    åıijå±ķ缮æłĩ
    -0.26
    ä¸įåħģ许
    -0.25
    goal
    -0.25
    缮æ¨Ļ
    -0.25
    uber
    -0.25
    POSITIVE LOGITS
     exploit
    0.30
    ENA
    0.29
     ISR
    0.27
    æİĴæ¯Ĵ
    0.27
    èĥľ
    0.26
     exploited
    0.26
    ena
    0.26
     utilization
    0.25
    ç¡Į
    0.25
    olina
    0.25
    Activations Density 0.057%

    No Known Activations