INDEX

Explanations

awk

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

è¿Ļç§įæĸ¹æ³ķ

-0.28

inct

-0.28

 independ

-0.28

amer

-0.27

éĻħ

-0.27

<AM

-0.26

éĥ¨

-0.26

pires

-0.26

æĿ¥çļĦ

-0.26

è·ĥ

-0.25

POSITIVE LOGITS

 Neighbor

0.28

è¾ĳ

0.28

 Ã¶d

0.27

 guiding

0.25

æĿĥçĽĬ

0.25

 guideline

0.25

ungen

0.25

åĲĮçĽŁ

0.25

 liberties

0.24

 angled

0.24

Activations Density 0.001%

awk

No Comments

No Known Activations