INDEX

Explanations

scan

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

 answering

-0.27

ql

-0.27

 Papers

-0.26

åĽĽé¡¹

-0.26

Getter

-0.26

getTime

-0.25

 unanswered

-0.24

-quarters

-0.24

è¡ħ

-0.24

å¹¸

-0.24

POSITIVE LOGITS

tee

0.29

çĲĨè§£åĴĮ

0.27

reserved

0.26

ocz

0.24

dee

0.24

owi

0.24

 reserved

0.24

idth

0.24

äºīè®®

0.24

çķĻä¸ĭæĿ¥

0.24

Activations Density 0.009%

scan

No Comments

No Known Activations