INDEX

Explanations

narrator

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

 tilt

-0.26

âĸĳ

-0.26

io

-0.26

è¿¹

-0.26

sa

-0.26

 âĸĳ

-0.25

IO

-0.25

 LinkedList

-0.24

 Spray

-0.24

-flow

-0.24

POSITIVE LOGITS

resco

0.27

æ¯Ķçİĩ

0.26

udes

0.25

å¹¶å¯¹

0.25

 impress

0.25

 brewers

0.25

èµ¢å¾Ĺ

0.24

Readable

0.24

æ²Ĳæµ´

0.24

ule

0.24

Activations Density 0.019%

narrator

No Comments

No Known Activations