© 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. 4-TRANSCODER-HP
    7. 250
    Prev
    Next
    INDEX
    Explanations

    Scientific/Technical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "context
    -0.27
    ä¸Ĭä¸ĭ
    -0.26
     Sen
    -0.26
    eman
    -0.25
    enis
    -0.25
    .browser
    -0.25
    _Parms
    -0.24
    è¿Ļè¯Ŀ
    -0.24
     developing
    -0.24
    def
    -0.23
    POSITIVE LOGITS
    icers
    0.27
    å¾¹
    0.27
    客è§Ĥ
    0.26
    å¥¥åľ°
    0.26
    çīĴ
    0.26
    urator
    0.25
    _suite
    0.25
    zier
    0.25
    utr
    0.25
    å¡Ķ
    0.24
    Activations Density 0.007%

    No Known Activations