© 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. 41073
    Prev
    Next
    INDEX
    Explanations

    Mixed article snippets

    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
    alist
    -0.33
    å¾®
    -0.30
     mic
    -0.27
    anism
    -0.26
     belie
    -0.26
     facebook
    -0.25
    Sharper
    -0.25
     spectator
    -0.25
    åı£è¢ĭ
    -0.25
    å¾®è§Ĥ
    -0.25
    POSITIVE LOGITS
    igung
    0.27
    åľ°åĮº
    0.25
    æĸ¹åľĨ
    0.25
    åħ³èģĶ
    0.24
    éªIJ
    0.24
     Organisation
    0.24
    mando
    0.24
    _REQUIRE
    0.24
    HEMA
    0.24
    åį³åı¯
    0.24
    Activations Density 0.592%

    No Known Activations