© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5430
    Prev
    Next
    INDEX
    Explanations

    centimeters

    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
    ering
    -0.27
    ัย
    -0.26
    ãģįãģ¦
    -0.25
    nce
    -0.24
     accord
    -0.24
    IVERS
    -0.23
    åħ¬åı¸ç«łç¨ĭ
    -0.23
    eer
    -0.23
     recovering
    -0.22
    ivers
    -0.22
    POSITIVE LOGITS
    åIJĦæł·
    0.29
    åħ¨å¤©
    0.25
    æ·Ģ
    0.24
    аÑĢа
    0.23
     inté
    0.23
    åĨĪ
    0.22
    anga
    0.22
    ernet
    0.21
     doubt
    0.21
    ('{{
    0.21
    Activations Density 1.658%

    No Known Activations