© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6191
    Prev
    Next
    INDEX
    Explanations

    or

    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
     positional
    -0.27
     stripes
    -0.27
     Bened
    -0.27
    BEL
    -0.27
    祯
    -0.25
    belt
    -0.25
    .cap
    -0.25
    éĨĴäºĨ
    -0.24
     cap
    -0.24
    EDIA
    -0.24
    POSITIVE LOGITS
     "','
    0.28
    身份
    0.25
    @Test
    0.25
    (ag
    0.25
     thresholds
    0.24
    uchar
    0.24
    åı¯è§Ĩ
    0.24
    ä½ĵè´¨
    0.24
     ag
    0.23
    !:
    0.23
    Activations Density 0.016%

    No Known Activations