© 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. 5320
    Prev
    Next
    INDEX
    Explanations

    ight

    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
    yw
    -0.28
    èĭŀ
    -0.26
    è°ģéĥ½
    -0.26
    楹
    -0.25
     unconditional
    -0.25
    éĻªä½ł
    -0.25
    éĤ´
    -0.24
    afil
    -0.24
    åĬŁè¯¾
    -0.24
    ãģªãģĹ
    -0.23
    POSITIVE LOGITS
    irl
    0.25
    èĸ®
    0.25
    ä¾Ī
    0.24
    æĬ¥ä»ĩ
    0.24
    åı°é£İ
    0.23
    èĵĦ
    0.23
     Tem
    0.23
     Publication
    0.23
    æݧ
    0.23
    Tem
    0.23
    Activations Density 0.033%

    No Known Activations