© 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. 63281
    Prev
    Next
    INDEX
    Explanations

    Web page snippets

    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
    missing
    -0.26
    ser
    -0.25
    ris
    -0.24
    #!
    -0.24
    Strength
    -0.24
     miss
    -0.23
    åŀ«
    -0.23
    æīŃ
    -0.23
    éĵ¶
    -0.23
    aware
    -0.23
    POSITIVE LOGITS
    =view
    0.30
     unf
    0.26
    emode
    0.26
    æŀģ大
    0.26
    ç§ijæĬĢèĤ¡ä»½
    0.26
    éķ¿çĽ¸
    0.25
    ãĥĪãĥ©
    0.25
    maxlength
    0.25
    vere
    0.24
     Authorized
    0.24
    Activations Density 6.996%

    No Known Activations