© 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. 111614
    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
     pé
    -0.26
     Owner
    -0.26
     continuation
    -0.26
    aris
    -0.24
    InlineData
    -0.24
    è¾¾
    -0.24
     interp
    -0.24
    辨
    -0.23
    ä¸Ńéĵģ
    -0.23
    arta
    -0.23
    POSITIVE LOGITS
    @d
    0.26
    æľĪåĪĿ
    0.26
    pton
    0.24
    @a
    0.24
    éŁ³é¢ij
    0.23
    çģ¶
    0.23
     collabor
    0.23
     encounters
    0.23
    ä¼ģä¸ļåıijå±ķ
    0.23
     chore
    0.22
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.