INDEX

Explanations

trap

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

@email

-0.30

elight

-0.28

 Ø§ÙĦØ³ÙĨ

-0.27

 curb

-0.26

éĥ¨ä»½

-0.26

âľī

-0.25

ç¨İè´¹

-0.24

æīŃçŁ©

-0.24

 commun

-0.24

æŀ°

-0.24

POSITIVE LOGITS

çī¹

0.28

ç´§

0.28

["

0.27

uttle

0.27

 stretch

0.26

ä»Ģä¹Ī

0.25

uming

0.25

æľºä¼ļ

0.25

è¯±

0.25

ulti

0.25

Activations Density 0.000%

trap

No Comments

No Known Activations