INDEX

Explanations

Lou

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 greedy

-0.27

ë¯¹

-0.26

åº¦è¿ĩ

-0.25

 latest

-0.24

 competence

-0.24

latest

-0.24

éĻĩ

-0.24

è¯´åĪ°è¿ĻéĩĮ

-0.23

.latest

-0.23

 compliment

-0.23

POSITIVE LOGITS

[arr

0.27

åĦ¿

0.27

æĭī

0.27

å¦¥åĸĦ

0.26

å»·

0.26

ãģ¼

0.26

æĭĪ

0.24

.setInt

0.24

kor

0.24

jian

0.24

Activations Density 0.002%

Lou

No Comments

No Known Activations