INDEX

Explanations

language and speech

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

ane

-0.30

 active

-0.28

 states

-0.28

 Stanford

-0.27

 state

-0.27

_states

-0.26

ofile

-0.26

 ACTIVE

-0.25

Active

-0.25

 runtime

-0.25

POSITIVE LOGITS

èµı

0.31

åī§åľº

0.30

è§£æĶ¾

0.26

{}.

0.26

 humid

0.24

æ¸ħåĩī

0.24

ç¹ģçĲĲ

0.24

))+

0.24

adora

0.24

 nudity

0.24

Activations Density 0.002%

language and speech

No Comments

No Known Activations