© 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. 20-TRANSCODER-HP
    7. 63832
    Prev
    Next
    INDEX
    Explanations

    addition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bler
    -0.27
    ogn
    -0.27
     trg
    -0.26
    otr
    -0.26
     Peer
    -0.26
    делÑĮ
    -0.25
    avier
    -0.24
    å½ĵãģ¦
    -0.23
    å®ŀè´¨
    -0.23
    忽è§Ĩ
    -0.23
    POSITIVE LOGITS
    åĩĨ
    0.28
    ÑģÑĤаÑĤ
    0.27
    åĪĨéĴŁåIJİ
    0.26
    äºĶåĪĨéĴŁ
    0.26
     bound
    0.26
    éĻĦè¿ij
    0.26
     ÑįкÑģ
    0.26
    æľ«
    0.26
    Bound
    0.25
    .gstatic
    0.25
    Activations Density 18.700%

    No Known Activations