© 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. 27-TRANSCODER-HP
    7. 9395
    Prev
    Next
    INDEX
    Explanations

    code and web text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -vers
    -0.28
    azole
    -0.27
    filled
    -0.26
    ocre
    -0.26
    æ¤Ĵ
    -0.25
    æĻºéĢł
    -0.25
    ()['
    -0.25
    -required
    -0.25
    masters
    -0.25
    unate
    -0.24
    POSITIVE LOGITS
    edis
    0.29
    ascal
    0.28
    itung
    0.27
    è¿Ļå¥Ĺ
    0.25
     Grimm
    0.25
    oscope
    0.24
     lem
    0.24
    æľĢ常è§ģçļĦ
    0.24
    egis
    0.24
    Samples
    0.23
    Activations Density 0.002%

    No Known Activations