© 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. 112275
    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
    åī¯å¸Ĥéķ¿
    -0.30
    ä¸įèĥ½åĨį
    -0.28
    ilig
    -0.25
    :pointer
    -0.25
    éĴ¿
    -0.24
    åĽ½éģĵ
    -0.24
     overarching
    -0.23
    èłķ
    -0.23
    éĤĵ
    -0.23
    Borders
    -0.23
    POSITIVE LOGITS
    _replace
    0.26
    çĸŁ
    0.24
    ä¿®çIJĨ
    0.24
    _ste
    0.23
     Lös
    0.23
    ³
    0.23
    ivre
    0.23
     lifespan
    0.23
     replace
    0.23
    ste
    0.23
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.