© 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. 7144
    Prev
    Next
    INDEX
    Explanations

    technical texts

    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
    æĸ¹å¼ıè¿Ľè¡Į
    -0.27
    anean
    -0.25
    vention
    -0.24
    nant
    -0.23
    (annotation
    -0.23
    æ¸ł
    -0.22
     yeti
    -0.22
     camel
    -0.22
    Directive
    -0.22
    å½±åĵįåĬĽ
    -0.22
    POSITIVE LOGITS
    ä¸Ŀä¸Ŀ
    0.27
    çĶŁæĹ¥
    0.26
    plus
    0.26
    oids
    0.25
    rop
    0.24
    estr
    0.24
    ouns
    0.24
    vides
    0.24
    Mah
    0.24
    OID
    0.23
    Activations Density 0.046%

    No Known Activations