© 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. 7028
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    缤
    -0.28
    缬
    -0.27
    vec
    -0.27
    adow
    -0.26
    械
    -0.26
    çĽĺ
    -0.26
     Prec
    -0.26
    楽
    -0.25
    ÄŁ
    -0.25
    _prec
    -0.25
    POSITIVE LOGITS
     unearth
    0.27
    æĸ¹å¼ıè¿Ľè¡Į
    0.27
    纵
    0.24
    åŁİå¸ĤçļĦ
    0.24
    thouse
    0.24
    对åħ¬åı¸
    0.24
    åıijåĩº
    0.23
     catch
    0.23
     acoustic
    0.23
    çĪ±åĽ½
    0.23
    Activations Density 0.048%

    No Known Activations