INDEX

Explanations

E

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

aurus

-0.28

à¸±à¸ĩ

-0.27

ationale

-0.27

ä¸ĭä¸Ģä¸ª

-0.27

º«

-0.26

este

-0.26

 ÐļÑĥ

-0.25

æīĴ

-0.25

åŃ¤

-0.25

ä¸ĭåįĬ

-0.25

POSITIVE LOGITS

æĹ¶åĪ»

0.30

 unconstitutional

0.27

 delegate

0.24

çļĦæł¹æľ¬

0.24

talk

0.24

delegate

0.24

 gÃ¼

0.24

å¢ŀ

0.23

 talk

0.23

spath

0.23

Activations Density 0.783%

E

No Comments

No Known Activations