© 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. 162375
    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
     germany
    -0.26
    满满
    -0.26
     applicationContext
    -0.25
    ä¿Ŀå¯Ĩ
    -0.25
     secrecy
    -0.25
    URA
    -0.25
    tower
    -0.24
    è°Īèµ·
    -0.24
    (vol
    -0.24
     Pros
    -0.24
    POSITIVE LOGITS
    éĩįè§Ĩ
    0.29
     provision
    0.27
     flesh
    0.26
    visor
    0.25
    VISION
    0.24
    Pictures
    0.24
     pre
    0.24
    éĿ©åij½
    0.24
     cry
    0.24
    æĹłåģ¿
    0.24
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.