© 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. 5345
    Prev
    Next
    INDEX
    Explanations

    negation

    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
    ends
    -0.28
    æĽ´å¥½
    -0.27
    esses
    -0.26
    lx
    -0.26
    ModelError
    -0.26
    ess
    -0.25
    laws
    -0.25
    åįķçĭ¬
    -0.25
    lessness
    -0.25
     ERR
    -0.25
    POSITIVE LOGITS
    .BL
    0.28
    antom
    0.27
    _BL
    0.25
    ocratic
    0.24
    (Buffer
    0.24
     wave
    0.23
    缸符
    0.23
    æļ´è·Į
    0.23
    DAL
    0.22
     sniff
    0.22
    Activations Density 0.066%

    No Known Activations