INDEX

Explanations

need

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 aside

-0.26

hoff

-0.26

 Telerik

-0.25

å¤¹

-0.25

éģŃåıĹ

-0.24

è¶³å¤Ł

-0.24

ä¸ºæŃ¤

-0.24

olum

-0.24

ko

-0.24

å²ģä»¥ä¸ĭ

-0.23

POSITIVE LOGITS

 needs

0.33

 Needs

0.31

needs

0.31

needed

0.30

 needed

0.29

 needing

0.28

Needed

0.28

_needed

0.28

-needed

0.27

anan

0.26

Activations Density 0.009%

need

No Comments

No Known Activations