© 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. 6972
    Prev
    Next
    INDEX
    Explanations

    Stop words

    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
    (strict
    -0.28
    æīįæĺ¯çľŁæŃ£
    -0.28
    MOST
    -0.28
    iences
    -0.28
    odable
    -0.27
     prive
    -0.27
    bish
    -0.26
    ohon
    -0.25
    ASTE
    -0.25
    ativas
    -0.25
    POSITIVE LOGITS
     Sym
    0.30
     F
    0.28
     f
    0.28
    éĩĮ
    0.26
    èĪ±
    0.26
    å¾Ħ
    0.25
    æĹ©
    0.25
     pools
    0.25
    h
    0.25
    约ä¼ļ
    0.25
    Activations Density 0.018%

    No Known Activations