INDEX

Explanations

non

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

cala

-0.30

ãĤĭãģĵãģ¨ãģ¯

-0.27

actor

-0.26

LAS

-0.25

æĲ¦

-0.24

TemplateName

-0.24

eron

-0.24

ibili

-0.23

quat

-0.23

ullen

-0.23

POSITIVE LOGITS

ä¸Ĭåİ»

0.29

å¤©èĬ±

0.26

 demo

0.26

demo

0.26

èĴĻ

0.25

æ´²

0.25

 Circle

0.24

olÃ³g

0.24

åľĪåŃĲ

0.24

 cerc

0.24

Activations Density 1.100%

non

No Comments

No Known Activations