INDEX

Explanations

even

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

æĪĲä»½

-0.30

æī¾å·¥ä½ľ

-0.29

åĩºå¤Ħ

-0.27

éĩįè¦ģæĦıä¹ī

-0.26

finish

-0.26

_End

-0.26

åĬĽè¿ĺæĺ¯

-0.25

alph

-0.25

inish

-0.25

educt

-0.24

POSITIVE LOGITS

ment

0.30

èģĶ

0.29

net

0.28

ä»£çĲĨ

0.28

lib

0.28

Âł

0.27

.net

0.27

 raining

0.27

 proxy

0.26

proxy

0.26

Activations Density 0.008%

even

No Comments

No Known Activations