INDEX

Explanations

one

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

 Isle

-0.25

Accessible

-0.24

æ²¡æĶ¶

-0.24

REFERENCES

-0.24

ense

-0.23

neider

-0.23

ascript

-0.23

AILS

-0.23

ensed

-0.23

ntity

-0.23

POSITIVE LOGITS

Quiet

0.24

éħį

0.24

rex

0.24

 truth

0.24

mith

0.24

arton

0.24

rex

0.23

uling

0.23

capt

0.23

éģĦ

0.23

Activations Density 16.388%

one

No Comments

No Known Activations