© 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. 63087
    Prev
    Next
    INDEX
    Explanations

    forum posts

    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
    åĶIJ
    -0.27
    éħĨ
    -0.27
    odesk
    -0.26
    OfSize
    -0.25
    åĪĩ
    -0.25
     porter
    -0.25
    æľ¬çĶ°
    -0.24
    çĻ¾
    -0.24
     EDM
    -0.24
    ISM
    -0.24
    POSITIVE LOGITS
    ..'
    0.28
    ãģĤãĤĬãģ¾ãģĹãģŁ
    0.26
    igar
    0.26
     CONF
    0.26
    _mgr
    0.25
    ponsors
    0.25
    Made
    0.24
    avid
    0.24
    ts
    0.24
    Clar
    0.24
    Activations Density 5.574%

    No Known Activations