INDEX

Explanations

of

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 :↵↵↵↵

-0.28

åĲįä¹ī

-0.27

éŁ§

-0.27

ä¸ŃåĽ½äºº

-0.26

å¤ĸè¡¨

-0.26

ItemImage

-0.26

è¶¾

-0.25

{}:

-0.25

notated

-0.25

ooth

-0.24

POSITIVE LOGITS

 streak

0.27

all

0.25

accumulator

0.25

ì²Ń

0.25

Stopping

0.24

 problem

0.24

 sort

0.24

 subject

0.24

almost

0.24

trace

0.24

Activations Density 0.012%

of

No Comments

No Known Activations