© 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. 5892
    Prev
    Next
    INDEX
    Explanations

    Technical/formal text

    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
    æ¶Ī失
    -0.43
     Elim
    -0.38
    Elim
    -0.38
     eliminate
    -0.38
    elim
    -0.37
    åħįéĻ¤
    -0.37
     disappears
    -0.36
    æĴ¤
    -0.35
     disappear
    -0.35
     eliminated
    -0.35
    POSITIVE LOGITS
    indh
    0.26
    HandlerContext
    0.26
    osite
    0.26
    _NEED
    0.25
    æķijåij½
    0.25
    liest
    0.24
    å¸Ń
    0.24
    _fixed
    0.24
    åį±
    0.24
    ndl
    0.24
    Activations Density 0.048%

    No Known Activations