INDEX

Explanations

Code syntax characters

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rome

-0.26

inator

-0.25

çŀİ

-0.25

Hip

-0.25

Hip

-0.25

hip

-0.24

dap

-0.24

ä¸Ģæ¥¼

-0.24

 DEAD

-0.24

vac

-0.24

POSITIVE LOGITS

 fetish

0.26

 balancing

0.26

çĥ½

0.25

 btnSave

0.25

.isFile

0.24

èĬ¾

0.24

èĪ·

0.24

éķ¿ä¹ħ

0.24

 '/../

0.23

agle

0.23

Activations Density 0.014%

Code syntax characters

No Comments

No Known Activations