© 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. 5799
    Prev
    Next
    INDEX
    Explanations

    Common filler words

    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
     virtue
    -0.28
    æĹ¥è¶ĭ
    -0.28
     pools
    -0.28
    agoon
    -0.27
    lation
    -0.27
     pri
    -0.25
     disturbance
    -0.25
    åħ¨éĿ¢åıijå±ķ
    -0.24
    éĺĦ
    -0.24
    è¿Ľä¸ĢæŃ¥
    -0.24
    POSITIVE LOGITS
    åģļä»Ģä¹Ī
    0.29
    åľ¨åĵªéĩĮ
    0.29
    åѦçĶŁä»¬
    0.27
    asking
    0.26
    elsen
    0.26
    orton
    0.26
    xAA
    0.26
    åĵªéĩĮ
    0.25
    ancers
    0.24
    èĤļåŃIJ
    0.24
    Activations Density 0.213%

    No Known Activations