INDEX

Explanations

post

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

(cond

-0.30

 ****************************************************************************

-0.28

 cond

-0.28

alytics

-0.28

éļª

-0.27

·¨

-0.27

 Cond

-0.26

cond

-0.26

ibel

-0.26

èĻº

-0.26

POSITIVE LOGITS

-blood

0.36

çģĮ

0.30

æ·ĺ

0.29

 begging

0.27

cest

0.25

íļĮ

0.25

)!

0.25

 tamil

0.24

 perf

0.24

ä¸Ģæ¬¾

0.24

Activations Density 0.009%

post

No Comments

No Known Activations