© 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. 20-TRANSCODER-HP
    7. 107929
    Prev
    Next
    INDEX
    Explanations

    Separated Documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĪĨå±Ģ
    -0.28
    èłķ
    -0.26
     Whip
    -0.25
    ritable
    -0.25
     Axios
    -0.25
    çĶ¨å¾®ä¿¡
    -0.25
    ahkan
    -0.25
    .PERMISSION
    -0.25
     Functions
    -0.25
    ä¸Ĭå¹´
    -0.24
    POSITIVE LOGITS
     disap
    0.27
    失
    0.27
    rib
    0.25
     UNS
    0.25
    hil
    0.24
     Speed
    0.23
    çļĦä¸Ģç§į
    0.23
     speed
    0.23
    æ²
    0.23
    access
    0.23
    Activations Density 16.408%

    No Known Activations