INDEX

Explanations

syndrome

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

çĻĤ

-0.33

eland

-0.29

ÐµÑĢÐ¸Ð°Ð»

-0.27

akh

-0.26

łģ

-0.25

adle

-0.25

çĦ¶

-0.25

è£ħå¤ĩ

-0.25

CHED

-0.24

 bÃ¤

-0.24

POSITIVE LOGITS

åı³è¾¹

0.27

æĺ¯ä¸Ģä»¶

0.26

ties

0.25

èĩ¼

0.25

nap

0.25

çĽĺçĤ¹

0.24

iston

0.24

æ²ģ

0.24

çļĦäººæĿ¥è¯´

0.24

ordinate

0.24

Activations Density 0.009%

syndrome

No Comments

No Known Activations