© 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. 12-TRANSCODER-HP
    7. 23126
    Prev
    Next
    INDEX
    Explanations

    ces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bevor
    -0.28
    è´¯éĢļ
    -0.28
     Fusion
    -0.26
    产èĥ½
    -0.26
    è¥¿çº¢æŁ¿
    -0.25
    çģ°å°ĺ
    -0.25
     Reform
    -0.25
    è¾ĥéķ¿
    -0.24
    伦
    -0.24
    Integration
    -0.23
    POSITIVE LOGITS
    anske
    0.28
    åĪĹ表
    0.27
     modifier
    0.26
     ATTRIBUTE
    0.26
    storeId
    0.25
     predictive
    0.24
    -symbol
    0.24
    åIJįåįķ
    0.24
    ocities
    0.23
    ité
    0.23
    Activations Density 0.000%

    No Known Activations