© 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. 14-TRANSCODER-HP
    7. 40903
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AILS
    -0.28
    ниÑĨÑĭ
    -0.27
    åĩŃä»Ģä¹Ī
    -0.27
    translator
    -0.27
    å¹´åĪĿ
    -0.26
    å¹´åĨħ
    -0.25
    é©»
    -0.25
    æīĵäºĨ
    -0.25
    ################################################
    -0.24
    integral
    -0.24
    POSITIVE LOGITS
    ctl
    0.28
    igit
    0.28
     bare
    0.26
    裸
    0.26
    ()._
    0.25
     ksztaÅĤt
    0.25
    wright
    0.25
     Felipe
    0.25
    irectional
    0.25
    è¯Ģ
    0.24
    Activations Density 0.362%

    No Known Activations

    This feature has no known activations.