INDEX

Explanations

service

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adia

-0.35

 Jackets

-0.28

richt

-0.28

ä¸Ģæľ¬

-0.27

ilater

-0.27

declaring

-0.26

èµ°äºĨ

-0.25

mitt

-0.24

è¡¥é½Ĳ

-0.24

ingham

-0.24

POSITIVE LOGITS

asm

0.30

ha

0.26

åŃº

0.25

du

0.25

è®½

0.25

 training

0.23

.scrollTo

0.23

du

0.23

é«ĺåº¦

0.23

Writable

0.23

Activations Density 0.031%

service

No Comments

No Known Activations