© 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. 130706
    Prev
    Next
    INDEX
    Explanations

    having

    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
    è¾Ħ
    -0.28
    ä¸ĢçĽ´åľ¨
    -0.28
     Hampton
    -0.24
    éĢĤçĶ¨äºİ
    -0.23
    á»Į
    -0.23
    èģĮ
    -0.23
    htub
    -0.23
     tutors
    -0.23
    enschaft
    -0.23
    ä¸Ģ缴æĺ¯
    -0.22
    POSITIVE LOGITS
    路人
    0.29
    |i
    0.27
    chia
    0.26
    isor
    0.25
    çĪ±å¥½
    0.25
    SL
    0.25
    å¾Ĺ罪
    0.25
    RH
    0.25
    åIJĥå¾Ĺ
    0.25
    /DTD
    0.25
    Activations Density 0.001%

    No Known Activations