INDEX

Explanations

first half

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

ater

-0.28

atel

-0.28

CJK

-0.27

è¢ħ

-0.27

ovolta

-0.27

 sequ

-0.26

ibrary

-0.26

 spawned

-0.26

Tip

-0.25

POSITIVE LOGITS

åĨ²çªģ

0.28

viz

0.28

ä¾ĭå¤ĸ

0.27

gsub

0.26

åħįè´£

0.24

[["

0.24

åľºæ¯ĶèµĽ

0.24

rado

0.24

erval

0.24

overrides

0.23

Activations Density 0.002%

first half

No Comments

No Known Activations