© 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. 19-TRANSCODER-HP
    7. 7849
    Prev
    Next
    INDEX
    Explanations

    and

    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
    éĴ»
    -0.27
    çļĦçĶŁåij½
    -0.26
    obia
    -0.25
    éĥ½çŁ¥éģĵ
    -0.25
    认åı¯
    -0.25
    认åIJĮ
    -0.24
    ç®į
    -0.24
    anon
    -0.24
    å¸Ļ
    -0.24
    Ñĥй
    -0.23
    POSITIVE LOGITS
    aby
    0.27
    çŃīåĨħ容
    0.26
    leground
    0.25
     arm
    0.25
     dumping
    0.25
    including
    0.24
     carc
    0.24
    äºĨå¤ļå°ij
    0.24
     sixteen
    0.24
    ilated
    0.24
    Activations Density 0.208%

    No Known Activations