INDEX

Explanations

Foreign language

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

wald

-0.29

hot

-0.28

asc

-0.25

dem

-0.25

.asc

-0.24

 Telecom

-0.24

spm

-0.23

acc

-0.23

quirer

-0.23

TableModel

-0.23

POSITIVE LOGITS

/sl

0.31

Sl

0.30

èĲ½åľ°

0.28

ç©¹

0.28

åŃ¤

0.27

chest

0.27

èĦ±è´«

0.27

åĵĳ

0.25

å¾ĭ

0.25

å¯¹å¾ħ

0.25

Activations Density 0.785%

Foreign language

No Known Activations