INDEX

Explanations

lawn

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.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

cold

-0.30

åĨ·

-0.29

åĨ°åĨ·

-0.29

↵↵↵↵↵↵↵↵↵↵

-0.27

Cold

-0.27

-0.25

lund

-0.25

Ð³Ð¾Ð´

-0.25

tatus

-0.25

 cold

-0.24

POSITIVE LOGITS

ship

0.26

HashCode

0.25

ackle

0.24

çľģåħ¬å®īåİħ

0.24

Arrays

0.23

cret

0.23

 fragments

0.23

èĩªè§ī

0.23

è±Ĩçĵ£

0.23

æ©¹

0.23

Activations Density 3.718%

lawn

No Comments

No Known Activations