© 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. 162526
    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
    .cp
    -0.32
    å¸ĤæķĻèĤ²å±Ģ
    -0.27
    gba
    -0.27
    éģ¿ãģij
    -0.26
    law
    -0.26
    .Documents
    -0.25
    lide
    -0.25
    lia
    -0.24
    çĶĵ
    -0.24
    olia
    -0.23
    POSITIVE LOGITS
    ivent
    0.26
    æŁIJä¸Ģ
    0.26
    	dto
    0.26
    ino
    0.25
    _('
    0.25
    æĢ»çļĦæĿ¥è¯´
    0.25
    æŁIJç§į
    0.25
    ãģĤãĤĭ
    0.24
     vet
    0.24
    éĶµ
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.