INDEX

Explanations

chain

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éķĲ

-0.28

min

-0.27

 carp

-0.25

 freeze

-0.24

åħµåĻ¨

-0.24

suppress

-0.24

freeze

-0.24

 suff

-0.24

ETA

-0.24

 Anch

-0.24

POSITIVE LOGITS

é¡¿

0.33

åĳ½

0.28

æ¯įäº²

0.27

·æĸ°

0.26

åİļ

0.26

æĵį

0.26

 Mand

0.25

?family

0.24

æľ¯

0.24

 Ð½Ð°ÑģÐµÐ»

0.24

Activations Density 0.035%

chain

No Comments

No Known Activations