© 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
    2. Qwen3-4B
    3. 19-TRANSCODER-HP
    4. 5368
    Prev
    Next
    INDEX
    Explanations

    Technical/scientific descriptions

    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
     lj
    -0.26
    continued
    -0.25
    WithError
    -0.25
    åįĵè¶Ĭ
    -0.25
    ewood
    -0.25
     peaked
    -0.24
     continued
    -0.24
    _subtype
    -0.24
    Continue
    -0.24
    åĪĩæį¢
    -0.24
    POSITIVE LOGITS
    å¼Ħ
    0.31
    ä¿Ŀå®Ī
    0.29
     unsuccessfully
    0.29
    fort
    0.28
     krat
    0.26
    æĥ³è±¡
    0.25
    éĩĭ
    0.25
    ocy
    0.24
    ä¼ļä¸Ĭ
    0.24
    éĩĬ
    0.24
    Activations Density 0.007%

    No Known Activations