INDEX

Explanations

regulatory

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

 Observatory

-0.27

.lua

-0.27

çĵľ

-0.26

vil

-0.26

obili

-0.26

ath

-0.25

vil

-0.24

 rais

-0.24

reas

-0.23

 olive

-0.23

POSITIVE LOGITS

 pymysql

0.26

æĭįæĭį

0.26

ument

0.25

 Bhar

0.25

 Burr

0.25

ecz

0.25

å¹ħ

0.25

imore

0.24

 mexico

0.24

 majors

0.24

Activations Density 0.002%

regulatory

No Comments

No Known Activations