© 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. 112705
    Prev
    Next
    INDEX
    Explanations

    Fields of study

    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
    ÑĤÑĥ
    -0.32
    ungs
    -0.28
    hap
    -0.26
    åį¬
    -0.24
    sgiving
    -0.24
    /terms
    -0.23
    urd
    -0.23
    å°½
    -0.23
    ãĥıãĤ¦ãĤ¹
    -0.23
    _INCLUDED
    -0.22
    POSITIVE LOGITS
    å®®
    0.25
    ä½ıäºĨ
    0.25
    Berry
    0.24
    太åŃIJ
    0.24
     Cage
    0.23
     sacr
    0.23
    journal
    0.23
    asca
    0.23
     dipl
    0.23
     journal
    0.23
    Activations Density 0.019%

    No Known Activations