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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87684
    Prev
    Next
    INDEX
    Explanations

    Truth and reality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actual
    -0.31
     perception
    -0.30
     days
    -0.27
    çľŁå¯¦
    -0.26
    isque
    -0.26
    actual
    -0.26
     Actual
    -0.26
    ernet
    -0.25
    _actual
    -0.25
     Perception
    -0.25
    POSITIVE LOGITS
    æĪ¿
    0.32
    åıĹçĽĬ
    0.28
    Attend
    0.28
    ä¸Ģ个éĩįè¦ģ
    0.27
    离ä¸įå¼Ģ
    0.26
    éĹ²ç½®
    0.26
    ä¸Ģå¹ħ
    0.25
    ãĤĤãģĨ
    0.25
    FAILURE
    0.25
    éĩįè¦ģåĨħ容
    0.24
    Activations Density 0.006%

    No Known Activations