INDEX

Explanations

organizations

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

ypy

-0.28

çĹ¨

-0.27

-ticket

-0.27

_ticket

-0.27

_hz

-0.25

ç³ł

-0.25

ä¹Łä¸įæĥ³

-0.25

empl

-0.25

è´Ńç¥¨

-0.25

ILA

-0.24

POSITIVE LOGITS

è¶³å¤Ł

0.27

mun

0.24

Mutable

0.24

ä¸ĸçķĮ

0.23

anford

0.23

 amort

0.23

Ã´i

0.23

.undefined

0.23

çĶ¸

0.23

 Bened

0.22

Activations Density 0.783%

organizations

No Comments

No Known Activations