© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5436
    Prev
    Next
    INDEX
    Explanations

    Th

    np_max-act · gemini-2.0-flash
    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
    arov
    -0.27
    åľ¨å¤ĸ
    -0.27
    æIJħæĭĮ
    -0.25
    ä»İæł¹æľ¬
    -0.25
     invite
    -0.25
    icorn
    -0.25
    å¤ĸåĽ´
    -0.24
    ikh
    -0.24
     Hers
    -0.24
    foot
    -0.23
    POSITIVE LOGITS
    -gen
    0.27
    spo
    0.25
    ellen
    0.24
    Ñģа
    0.24
     ÑģообÑīаеÑĤ
    0.24
    eta
    0.24
    SM
    0.24
    oo
    0.23
    èŀį
    0.23
    olation
    0.22
    Activations Density 0.000%

    No Known Activations