INDEX

Explanations

original

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

at

-0.28

-next

-0.28

çĤ¹å¤ļ

-0.27

sun

-0.26

inson

-0.26

ç®¡

-0.26

concept

-0.26

ates

-0.25

POSITIVE LOGITS

åªĴ

0.26

 postId

0.26

è°Īè®º

0.25

å¯Ĩåº¦

0.25

ä¹ĭåĬ¿

0.24

ÑĪÐ°

0.24

 posing

0.24

goog

0.24

ä¸Ģç¯ĩæĸĩç«ł

0.23

 afterward

0.23

Activations Density 0.005%

original

No Comments

No Known Activations