© 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. 97646
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    iller
    -0.29
    uba
    -0.27
    该游æĪı
    -0.26
    rai
    -0.26
    aska
    -0.26
    çĮİ
    -0.25
    wan
    -0.25
    fcc
    -0.25
    æīĵå¼ĢäºĨ
    -0.25
    rait
    -0.24
    POSITIVE LOGITS
    ::-
    0.27
     Äijảo
    0.26
    ếu
    0.24
    (diff
    0.24
    hos
    0.24
     quoi
    0.23
     Mat
    0.23
    dest
    0.23
    ACITY
    0.23
    Anonymous
    0.23
    Activations Density 3.224%

    No Known Activations

    This feature has no known activations.