INDEX

Explanations

Specific names and technical descriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ï¼Ł↵

-0.27

åħ¬å¼Ģ

-0.26

åĲĪæ³ķ

-0.26

 explicit

-0.24

å·¥

-0.24

åĲĪ

-0.24

è¿ĻéĩĮ

-0.23

ä¹ĭæīĢä»¥

-0.23

uar

-0.23

ï¼Ł↵↵

-0.23

POSITIVE LOGITS

via

0.44

 using

0.43

via

0.38

 based

0.38

åŁºäºİ

0.36

Via

0.35

due

0.34

using

0.34

Via

0.32

åĩŃåĢŁçĿĢ

0.32

Activations Density 0.001%

Specific names and technical descriptions

No Comments

No Known Activations