© 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. 5462
    Prev
    Next
    INDEX
    Explanations

    used

    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
     affine
    -0.28
     combination
    -0.27
    complexType
    -0.27
     Aff
    -0.27
    ixer
    -0.27
    åĬłä¸Ĭ
    -0.26
     propre
    -0.26
    antage
    -0.26
    ored
    -0.26
    åĦ¿
    -0.25
    POSITIVE LOGITS
    èµĦ讯
    0.28
    们çļĦ
    0.26
    &page
    0.25
    éĩijå±±
    0.25
    mdl
    0.25
    eltas
    0.25
    ))?
    0.24
    lia
    0.24
    hill
    0.24
    tel
    0.24
    Activations Density 0.328%

    No Known Activations