© 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. 98750
    Prev
    Next
    INDEX
    Explanations

    News and current events

    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
    èĩªçĦ¶
    -0.32
     natural
    -0.31
     Natural
    -0.28
    hed
    -0.27
    oen
    -0.26
     Ages
    -0.26
    )||(
    -0.25
    åĩĨæŶ
    -0.24
    æĢ»èµĦ产
    -0.24
     soc
    -0.24
    POSITIVE LOGITS
     controversial
    0.42
    é£İæ³¢
    0.41
     controversy
    0.41
    äºīè®®
    0.40
     scandals
    0.36
     controversies
    0.35
     scandal
    0.35
    Bug
    0.35
    æĬĹè®®
    0.35
    严éĩįçļĦ
    0.34
    Activations Density 0.009%

    No Known Activations