INDEX

Explanations

Medical

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

.bus

-0.30

COMPARE

-0.25

éĴĹ

-0.24

upert

-0.24

ä¸Ģå¿ĥ

-0.24

(bus

-0.24

 provinc

-0.23

èŀįåªĴä½ĵ

-0.23

 patrons

-0.23

 Provincial

-0.23

POSITIVE LOGITS

é«ĺå¼ºåº¦

0.27

çĲĨæĥ³çļĦ

0.26

manual

0.25

/providers

0.25

ä¸įéĶĻ

0.24

èĢĮæĺ¯

0.24

áº¯c

0.24

 Farr

0.24

MAP

0.24

}):

0.23

Activations Density 0.001%

Medical

No Comments

No Known Activations