© 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. 32-TRANSCODER-HP
    7. 43728
    Prev
    Next
    INDEX
    Explanations

    Immune cell infiltration

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rama
    -0.27
    ÑĢÑĥÑģ
    -0.26
    aled
    -0.26
    cir
    -0.26
    æĶ¹éĿ©åĪĽæĸ°
    -0.25
    éªĸ
    -0.25
    воз
    -0.24
    ovan
    -0.24
    cion
    -0.23
    uzu
    -0.23
    POSITIVE LOGITS
    津贴
    0.32
     polym
    0.31
     pm
    0.27
    褫
    0.27
     poll
    0.26
    æĥ³è¿ĩ
    0.25
    PM
    0.25
     PM
    0.25
    poll
    0.25
    表çİ°
    0.24
    Activations Density 0.010%

    No Known Activations