© 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. 14-TRANSCODER-HP
    7. 41315
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Down
    -0.28
    好å¥ĩå¿ĥ
    -0.28
    ä¸ĩ
    -0.27
     Universal
    -0.27
    down
    -0.26
    Ĥ¬
    -0.26
    mc
    -0.25
    çģ«æĺŁ
    -0.25
    soc
    -0.25
     plat
    -0.25
    POSITIVE LOGITS
    åĩºå¤Ħ
    0.28
    hire
    0.26
    ño
    0.26
    ä»ĸçŁ¥éģĵ
    0.26
    .mit
    0.25
    inal
    0.24
    å½ĵä»ĸ
    0.24
    åħĥç´ł
    0.24
    besch
    0.24
    imity
    0.23
    Activations Density 0.085%

    No Known Activations

    This feature has no known activations.