© 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. 111702
    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
    çIJĨçĶ±
    -0.27
    ges
    -0.26
     idea
    -0.26
    ä½ĵç³»
    -0.24
     loosely
    -0.24
     bil
    -0.24
     same
    -0.23
     nutshell
    -0.23
    çŁ¾
    -0.23
     ideas
    -0.23
    POSITIVE LOGITS
    ä¸Ģ段
    0.28
    éĢģè´§
    0.26
    åĽ½å®¶å®īåħ¨
    0.24
    awi
    0.24
    tractor
    0.24
    lat
    0.23
    å°ģ
    0.23
    Allow
    0.23
    Token
    0.23
     xuân
    0.23
    Activations Density 0.026%

    No Known Activations

    This feature has no known activations.