INDEX

Explanations

development, growth

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

èī¯

-0.31

å¼Ĥ

-0.27

subcategory

-0.27

èĥª

-0.26

emon

-0.25

 subt

-0.25

elier

-0.25

minimum

-0.25

ivative

-0.24

Zy

-0.24

POSITIVE LOGITS

 Vince

0.24

Opaque

0.23

 fflush

0.23

éĶµ

0.23

å¹³è¡¡

0.23

!:

0.23

 Oscars

0.22

Reach

0.22

 Snape

0.22

è¿Ľåĩº

0.22

Activations Density 0.001%

development, growth

No Comments

No Known Activations