INDEX

Explanations

"Enter" key or entering text

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

ollo

-0.32

-caret

-0.27

ethe

-0.27

è´¨éĩıåĴĮ

-0.27

çĸ¾çĹħçļĦ

-0.27

ÃŃcio

-0.26

arkers

-0.25

sno

-0.24

reach

-0.24

tte

-0.24

POSITIVE LOGITS

okin

0.26

.Pull

0.24

 unlucky

0.24

ä¸Ńåħ³æĿĳ

0.24

ivalent

0.24

å¯Į

0.24

 owned

0.24

Lod

0.24

.adj

0.23

å¥ī

0.23

Activations Density 0.002%

"Enter" key or entering text

No Comments

No Known Activations