INDEX

Explanations

Jeffrey

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

anka

-0.35

joining

-0.27

åº¸

-0.25

 Stam

-0.25

æľĪä»½

-0.24

.setFill

-0.24

moy

-0.24

MMC

-0.23

è¿Ļæł·çļĦ

-0.23

 '\''

-0.23

POSITIVE LOGITS

_bottom

0.29

oola

0.28

 Bottom

0.27

èĤ¤èī²

0.27

Bottom

0.27

âľĹ

0.27

 Trust

0.26

thood

0.25

 adulthood

0.25

 Kern

0.25

Activations Density 0.157%

Jeffrey

No Comments

No Known Activations