© 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. 5183
    Prev
    Next
    INDEX
    Explanations

    Michael

    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
    åĿıäºĭ
    -0.24
    侥幸
    -0.23
    ä¸Ģç§į
    -0.23
     Pou
    -0.22
    ÙĨ
    -0.22
    safe
    -0.22
    å«ģ
    -0.21
     lượt
    -0.21
     courthouse
    -0.21
    subst
    -0.21
    POSITIVE LOGITS
    kek
    0.25
    yas
    0.24
    çī¯
    0.22
    adt
    0.22
    Fx
    0.22
     eagle
    0.22
    hof
    0.21
     обеÑģп
    0.21
    elves
    0.21
    å¾Ħ
    0.21
    Activations Density 2.198%

    No Known Activations