INDEX

Explanations

ot

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

ileo

-0.26

 Reply

-0.26

 regain

-0.26

side

-0.25

åĲĪèµĦ

-0.25

å¤Ļ

-0.25

 side

-0.24

ained

-0.24

 Recover

-0.24

 recover

-0.24

POSITIVE LOGITS

 lids

0.27

mins

0.26

 Compatible

0.25

 Ð¾ÑĢÐ¸Ð³

0.25

VisualStyle

0.24

éĢŁçİĩ

0.24

 geme

0.24

 prim

0.24

ä¸ĵåĳĺ

0.24

ãģĻãĤĭãģ®ãģ¯

0.24

Activations Density 0.002%

ot

No Comments

No Known Activations