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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5165
    Prev
    Next
    INDEX
    Explanations

    Possessive pronouns

    np_max-act · gemini-2.0-flash
    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
    çĻ»è®°
    -0.29
    派驻
    -0.27
    è§Ĩå¯Ł
    -0.26
    çĪ±å¥ĩ
    -0.25
     counter
    -0.24
    icycle
    -0.24
    å½ĵæŶçļĦ
    -0.24
    é¢ĨåŁŁ
    -0.24
     cycle
    -0.24
    _party
    -0.24
    POSITIVE LOGITS
     ourselves
    0.42
    æĪij们çļĦ
    0.39
    æĪij们åºĶ该
    0.36
    æĪij们å¿ħé¡»
    0.34
    æĪij们éľĢè¦ģ
    0.33
     ìļ°ë¦¬ê°Ģ
    0.32
    æĪij们
    0.32
    åĽłä¸ºæĪij们
    0.31
    å¦ĤæŀľæĪij们
    0.31
     our
    0.31
    Activations Density 0.234%

    No Known Activations