© 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. 22-TRANSCODER-HP
    7. 112478
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.27
     ==(
    -0.26
    å¹²æ¶ī
    -0.25
    æĭĶ
    -0.24
     Remarks
    -0.24
    åĶ¯ä¸ĢçļĦ
    -0.24
     implication
    -0.24
     Mus
    -0.24
    @@
    -0.23
    ıkl
    -0.23
    POSITIVE LOGITS
    çĬį
    0.27
    issan
    0.27
    åIJĥäºĨ
    0.26
    æ·±åĪĩ
    0.26
     relief
    0.23
    è·Łå¥¹
    0.23
     Vend
    0.23
     firing
    0.23
    å°ıå§IJå§IJ
    0.23
    çĽ´è¾¾
    0.23
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.