© 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. 107706
    Prev
    Next
    INDEX
    Explanations

    Programming forum questions

    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
    !,
    -0.28
    请æĤ¨
    -0.26
    æ¹ĥ
    -0.26
    åķ¦
    -0.25
    ilar
    -0.24
    :,
    -0.24
    å¹¼åĦ¿åĽŃ
    -0.24
    oenix
    -0.24
     dig
    -0.24
    uste
    -0.23
    POSITIVE LOGITS
    entionPolicy
    0.28
    ä¹ī
    0.27
    éĵĥ
    0.26
    åĽłåľ°åĪ¶å®ľ
    0.25
     cubes
    0.25
     icing
    0.25
    ä¸įæŃ»
    0.25
    éĴŁ
    0.24
     Principle
    0.24
    _msgs
    0.24
    Activations Density 4.760%

    No Known Activations