INDEX

Explanations

Suffixes ending in "o"

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ly

-0.38

nya

-0.31

urate

-0.29

ness

-0.28

sWith

-0.28

ns

-0.27

nie

-0.27

nh

-0.25

nil

-0.25

ne

-0.24

POSITIVE LOGITS

quals

0.30

ÅĽÄĩ

0.28

äºĨä¸ĢäºĽ

0.27

Ùĭ

0.26

lette

0.26

ÑģÑĤÑĮ

0.26

ctrine

0.25

ä»ĸä»¬æĺ¯

0.25

tow

0.25

expert

0.24

Activations Density 0.418%

Suffixes ending in "o"

No Comments

No Known Activations