INDEX

Explanations

scaling

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

 lanc

-0.28

XT

-0.27

_HOOK

-0.26

LOTS

-0.25

èĵŁ

-0.25

 Hutch

-0.25

RY

-0.25

ä¾Ľè´§

-0.25

POSITIVE LOGITS

åıĪè¢«

0.31

æļĳ

0.28

bilt

0.28

 intuit

0.26

æĿĨèıĮ

0.26

æ¦»

0.26

bred

0.26

winter

0.25

åĲĦéĥ¨éĹ¨

0.25

ç³Ļ

0.25

Activations Density 0.021%

scaling

No Comments

No Known Activations