INDEX

Explanations

navigational, environmental cues

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

å¡«è¡¥

-0.29

åīįæīĢ

-0.29

Ø²ÙĦ

-0.27

INGER

-0.27

çĹī

-0.25

Ð·Ð½Ð°

-0.24

WithName

-0.24

yh

-0.23

ymbols

-0.23

ByName

-0.23

POSITIVE LOGITS

æĿĥåĪ©

0.27

 also

0.25

 mediator

0.25

than

0.25

cog

0.24

èĬĴ

0.24

æīĭå¥Ĺ

0.24

åĢĻéĢī

0.24

ä¹Łè¦ģ

0.24

 analyse

0.24

Activations Density 0.002%

navigational, environmental cues

No Comments

No Known Activations