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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 6032
    Prev
    Next
    INDEX
    Explanations

    legal and contractual contexts

    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
    license
    -0.28
    åĩĨåĪĻ
    -0.25
    recommended
    -0.25
     recommand
    -0.25
     recommended
    -0.25
     má»ĩnh
    -0.24
     Pru
    -0.24
    åı¯æĥľ
    -0.24
    }?
    -0.24
    æĺ¯æĪijçļĦ
    -0.24
    POSITIVE LOGITS
    ewater
    0.27
    eros
    0.27
    rin
    0.25
    etime
    0.25
     sessions
    0.24
    ERA
    0.24
    apters
    0.23
    å¡«è¡¥
    0.23
    ulk
    0.23
     at
    0.23
    Activations Density 0.184%

    No Known Activations