© 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. 29765
    Prev
    Next
    INDEX
    Explanations

    catch

    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
    agna
    -0.29
    BN
    -0.28
    CN
    -0.28
    CMD
    -0.27
    IN
    -0.27
    пÑĢоÑģ
    -0.26
    _PR
    -0.26
    æ°°
    -0.25
    aN
    -0.25
     NZ
    -0.25
    POSITIVE LOGITS
    çĤ¹äº®
    0.27
    worm
    0.27
    ä»ħ代表
    0.27
     assassin
    0.25
    favor
    0.24
    umba
    0.24
     belts
    0.24
    avic
    0.24
    ä¸Ŀ绸ä¹ĭè·¯
    0.24
     silk
    0.23
    Activations Density 0.811%

    No Known Activations