INDEX

Explanations

Code

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

clud

-0.26

uum

-0.26

 breeze

-0.25

æ²£

-0.25

éħĴç²¾

-0.24

çŁĽçĽ¾

-0.24

åģ¥åº·

-0.23

 prÃ©s

-0.23

ubber

-0.23

Pager

-0.23

POSITIVE LOGITS

mph

0.24

çķ´

0.24

ori

0.23

éĥĦ

0.23

 DARK

0.23

 REFERENCES

0.23

 Broadcast

0.23

åī¥

0.23

privacy

0.23

cname

0.23

Activations Density 0.061%

Code

No Comments

No Known Activations