INDEX

Explanations

technique

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÑģÑĤÐ²ÐµÐ½Ð½ÑĭÐµ

-0.28

fon

-0.27

ientos

-0.27

ä¸īä»£

-0.26

ÑģÑĤÐ°Ð½Ð°Ð²

-0.26

SenderId

-0.25

uess

-0.25

 Brands

-0.24

AGES

-0.24

EEE

-0.24

POSITIVE LOGITS

 techniques

0.33

æĬĢèīº

0.28

ç»£

0.27

 technique

0.26

æĶ¯éĺŁ

0.26

 Techniques

0.25

æ®¿

0.25

soever

0.25

 slipped

0.25

æĬĢæ³ķ

0.24

Activations Density 22.386%

technique

No Comments

No Known Activations