© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7249
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulu
    -0.27
    è¶ĭåĬ¿
    -0.26
    iability
    -0.25
    å½ĸ
    -0.25
     someday
    -0.25
     trend
    -0.25
    对çŃĸ
    -0.25
    çĭ®åŃIJ
    -0.24
    ea
    -0.24
    erb
    -0.24
    POSITIVE LOGITS
    менно
    0.28
    SUPER
    0.26
     perm
    0.26
    *d
    0.26
    *e
    0.24
     Vita
    0.23
    иÑĢÑĥеÑĤ
    0.23
     Undert
    0.23
    -face
    0.23
    *sin
    0.23
    Activations Density 0.088%

    No Known Activations

    This feature has no known activations.