© 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. 5411
    Prev
    Next
    INDEX
    Explanations

    Both

    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
    оÑĦ
    -0.30
    æľī没æľī
    -0.27
    ä¸ĢéĿ¢
    -0.26
    è¿ĺæĥ³
    -0.26
    éIJ
    -0.25
    uzu
    -0.25
    uin
    -0.24
    OfFile
    -0.24
     Cra
    -0.24
    Mom
    -0.24
    POSITIVE LOGITS
     nom
    0.27
     mand
    0.25
    å»Ĭ
    0.24
    ORITY
    0.24
     sei
    0.24
     NO
    0.24
     bet
    0.24
    nom
    0.23
     parenthesis
    0.23
     Harr
    0.23
    Activations Density 0.040%

    No Known Activations