© 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. 19-TRANSCODER-HP
    7. 8240
    Prev
    Next
    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ©æĻļ
    -0.34
    æĹ©
    -0.28
     Linden
    -0.25
    _orient
    -0.24
    gmail
    -0.24
    _macros
    -0.23
    æĹ©çĤ¹
    -0.23
    ëłµ
    -0.23
     blessed
    -0.23
    yar
    -0.23
    POSITIVE LOGITS
     slips
    0.31
     slip
    0.28
    arf
    0.27
    ä¸Ģéĥ¨åĪĨ
    0.26
     scaffold
    0.26
    大æī¹
    0.25
     integral
    0.25
    flu
    0.24
     joint
    0.24
    inqu
    0.24
    Activations Density 0.035%

    No Known Activations