© 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. 14-TRANSCODER-HP
    7. 40157
    Prev
    Next
    INDEX
    Explanations

    Web addresses/handles/code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĮĤçīĮ
    -0.26
    olle
    -0.26
    éĶ¤
    -0.25
    çŃ¾çº¦
    -0.25
    “(
    -0.25
     imageURL
    -0.24
    ",(
    -0.24
    æĺĻ
    -0.24
     =~
    -0.24
    AMB
    -0.24
    POSITIVE LOGITS
    imitive
    0.29
    tees
    0.28
    <title
    0.26
    gua
    0.26
    erea
    0.26
    изаÑĨиÑı
    0.25
     hole
    0.25
    erg
    0.25
    igua
    0.25
    quam
    0.25
    Activations Density 0.121%

    No Known Activations