© 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. 107344
    Prev
    Next
    INDEX
    Explanations

    technical writings/patents

    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
    ActionTypes
    -0.29
     themselves
    -0.27
    IOD
    -0.26
    ",[
    -0.25
    æIJĵ
    -0.24
    ä»ĸä¹Ł
    -0.23
    á»į
    -0.23
    çĶ¨å¾®ä¿¡
    -0.23
     Catal
    -0.23
    ä»»ä½ķ人
    -0.23
    POSITIVE LOGITS
    è¶Ĭ
    0.31
    å²Ń
    0.29
    æĴĩ
    0.28
    ousel
    0.28
    ErrorException
    0.25
    urray
    0.25
    èģ
    0.24
     оÑģÑĤа
    0.24
    sns
    0.23
    æ²½
    0.23
    Activations Density 0.393%

    No Known Activations