© 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. 8095
    Prev
    Next
    INDEX
    Explanations

    software

    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
    åĩ¤
    -0.26
    ikut
    -0.26
    thest
    -0.25
    常åĬ¡åī¯
    -0.25
    åİķ
    -0.24
    elor
    -0.24
    ese
    -0.24
    aggable
    -0.24
    bes
    -0.24
     potentially
    -0.24
    POSITIVE LOGITS
    å¾ij
    0.30
    å¾Ħ
    0.30
    &r
    0.26
    ấp
    0.25
    æ¼²
    0.25
     Partition
    0.25
    partition
    0.25
    ä¹ŁæĪIJ为
    0.25
    haar
    0.25
     jd
    0.25
    Activations Density 0.062%

    No Known Activations