© 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. 9-TRANSCODER-HP
    7. 29642
    Prev
    Next
    INDEX
    Explanations

    setting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä½łä»¥ä¸º
    -0.27
    apos
    -0.26
    æĿ¥åĪ°äºĨ
    -0.26
    SETTING
    -0.26
    au
    -0.26
    /xml
    -0.25
    ä¸įæŃ»
    -0.25
     paris
    -0.25
    çĬĢ
    -0.25
    ariat
    -0.25
    POSITIVE LOGITS
     Overrides
    0.27
    ulet
    0.25
     TestBed
    0.25
     attractiveness
    0.24
    ayout
    0.24
    rics
    0.24
     pumps
    0.24
     ...↵
    0.23
    æķĪ
    0.23
    ixel
    0.23
    Activations Density 2.338%

    No Known Activations