INDEX

Explanations

collective

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

åĲĪçĲĨçļĦ

-0.28

orth

-0.27

ç½Ł

-0.26

 setHidden

-0.26

å·¥ä¸ļ

-0.25

=temp

-0.25

çķ¸

-0.24

emy

-0.24

æĹıèĩªæ²»å·ŀ

-0.24

	Spring

-0.24

POSITIVE LOGITS

é©¾

0.33

 authenticity

0.27

ewater

0.25

raud

0.25

 bonded

0.24

è¯ļä¿¡

0.24

illery

0.24

.issue

0.24

çĤ¹çĩĥ

0.23

èĬĤæ°´

0.23

Activations Density 0.021%

collective

No Comments

No Known Activations