© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163366
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ign
    -0.27
    好åĥı
    -0.27
     Implements
    -0.26
    è¿«
    -0.26
    props
    -0.26
    	prop
    -0.24
    	props
    -0.24
    INGS
    -0.24
    å¼Ĥ
    -0.24
    prop
    -0.23
    POSITIVE LOGITS
     moons
    0.27
    ç»ĵæŀĦæĢ§
    0.26
    ãĤ¸ãĥ¼
    0.26
    @js
    0.25
     pull
    0.24
    åĪĨ彩
    0.23
    Sit
    0.23
    并å°Ĩ
    0.23
    æ°ij主çĶŁæ´»
    0.23
    çļĦç¼ĺ
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.