© 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. 24-TRANSCODER-HP
    7. 149710
    Prev
    Next
    INDEX
    Explanations

    role

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ»ķ
    -0.26
    quito
    -0.26
    jam
    -0.25
    unist
    -0.25
    å°Ĩ以
    -0.25
     Framework
    -0.24
    åİĨ
    -0.24
    dda
    -0.24
    Toolkit
    -0.24
    eded
    -0.24
    POSITIVE LOGITS
     пÑĢиÑĩ
    0.28
    ç¬ijæĦı
    0.26
    $con
    0.25
    inaire
    0.25
    dess
    0.25
     pourquoi
    0.25
    clr
    0.24
    posit
    0.24
    åįĥ亿
    0.24
    åİŁåĽłä¹ĭä¸Ģ
    0.24
    Activations Density 0.237%

    No Known Activations