© 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. 64093
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æ¯ĶåĪ©
    -0.33
    ç°Ł
    -0.27
    opa
    -0.26
    orio
    -0.26
    ixel
    -0.25
     Ferdinand
    -0.25
    éĤ»
    -0.24
    å·²çĦ¶
    -0.24
    ãĥĭãĥ³ãĤ°
    -0.24
     consolidate
    -0.24
    POSITIVE LOGITS
    ä¸ĩçī©
    0.27
    åĨį
    0.26
     insider
    0.26
     Mant
    0.26
    SOLE
    0.25
     TEntity
    0.25
    holm
    0.25
     term
    0.24
    åĻİ
    0.24
    ÙĪار
    0.24
    Activations Density 4.035%

    No Known Activations

    This feature has no known activations.