© 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. 19-TRANSCODER-HP
    7. 5805
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑģÑĤÑĥп
    -0.25
    çĻĸ
    -0.24
    å±ģ
    -0.24
    å±ģèĤ¡
    -0.24
    请è¾ĵåħ¥
    -0.24
    *ft
    -0.24
    æĹłæķĮ
    -0.24
    план
    -0.24
     victim
    -0.23
    亢
    -0.23
    POSITIVE LOGITS
    ëĦ·
    0.27
     comple
    0.26
     disc
    0.25
    »¿
    0.25
     contingency
    0.24
     natur
    0.24
     masking
    0.24
     cer
    0.24
    ;display
    0.24
    itational
    0.23
    Activations Density 0.012%

    No Known Activations

    This feature has no known activations.