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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 63716
    Prev
    Next
    INDEX
    Explanations

    code class

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsur
    -0.31
     Pager
    -0.28
    isme
    -0.28
    ä¸įçķĻ
    -0.28
    ismo
    -0.27
    åıªä¸įè¿ĩ
    -0.25
    è¯Ń
    -0.25
    .nodeType
    -0.25
    ýt
    -0.25
    ãĤıãģijãģ§ãģĻ
    -0.24
    POSITIVE LOGITS
    _xor
    0.28
     Äijôi
    0.28
    æ°ijéĹ´
    0.27
    å¼Ģ
    0.27
     Ground
    0.26
     Borrow
    0.25
     cons
    0.24
    éĺ»
    0.24
    uard
    0.23
    çĤĸ
    0.23
    Activations Density 5.007%

    No Known Activations