© 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. 20-TRANSCODER-HP
    7. 108063
    Prev
    Next
    INDEX
    Explanations

    Systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĪĸèĢħåħ¶ä»ĸ
    -0.29
    OCI
    -0.29
    gende
    -0.27
    (CG
    -0.26
    éĻĪæŁIJ
    -0.26
    (ag
    -0.26
    æĪĸåħ¶ä»ĸ
    -0.26
    acen
    -0.25
    paired
    -0.24
    auge
    -0.24
    POSITIVE LOGITS
    èĢģå¸ĪçļĦ
    0.27
     à¹Ĩ
    0.26
    à¹Ĩ
    0.26
    ieÅĦ
    0.24
    åĩºå¤Ħ
    0.24
    ism
    0.24
    å¤ķ
    0.24
    Extent
    0.24
    /place
    0.24
     sÆ°
    0.23
    Activations Density 63.047%

    No Known Activations