© 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. 35-TRANSCODER-HP
    7. 40099
    Prev
    Next
    INDEX
    Explanations

    Code and markup languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âm
    -0.28
     anything
    -0.27
     professionalism
    -0.26
    é¡¹çĽ®çļĦ
    -0.26
    actly
    -0.25
     entreg
    -0.24
     everybody
    -0.24
    оÑģÑĤоÑı
    -0.24
    _starts
    -0.24
     yours
    -0.24
    POSITIVE LOGITS
    缸åħ³
    0.47
     relevant
    0.46
     related
    0.38
     Relevant
    0.36
    relevant
    0.35
    ablo
    0.31
     required
    0.29
     pertinent
    0.29
    缸åħ³åĨħ容
    0.28
    çļĦ缸åħ³
    0.28
    Activations Density 0.997%

    No Known Activations