INDEX

Explanations

UN

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

 Worse

-0.28

ä¸ĩéĩĮ

-0.28

å¹¸

-0.28

åħį

-0.27

 Crash

-0.27

[âĢ¦

-0.26

.pref

-0.26

ju

-0.26

ä¾ĺ

-0.26

[âĢ¦]

-0.26

POSITIVE LOGITS

RY

0.28

reeze

0.26

Ryan

0.26

å¿ĥæĢĿ

0.26

XA

0.24

 Ryan

0.24

çº¯æ´ģ

0.24

 instinct

0.23

*>*

0.23

 dein

0.23

Activations Density 0.785%

UN

No Comments

No Known Activations