INDEX

Explanations

semantic

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

éŃĦ

-0.29

erate

-0.28

opard

-0.27

åĲĮæľŁ

-0.27

ä¸ĢæľŁ

-0.27

 paran

-0.26

æľĢä½³

-0.25

ually

-0.25

remaining

-0.25

æľĢåħ·

-0.25

POSITIVE LOGITS

sil

0.27

 bÃ¼

0.27

onders

0.26

ÑĭÐ²Ð°

0.25

ved

0.25

ados

0.24

 dough

0.24

æ´½

0.24

å±ŀ

0.24

babel

0.24

Activations Density 0.040%

semantic

No Comments

No Known Activations