INDEX

Explanations

latter

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

eld

-0.27

earn

-0.26

 town

-0.26

çĮ«

-0.26

PM

-0.25

ä¸ľè¥¿

-0.25

æģ»

-0.25

 Casc

-0.24

.cs

-0.24

PM

-0.23

POSITIVE LOGITS

orts

0.28

æĹ¶ä»£çļĦ

0.28

pany

0.28

OMETRY

0.27

ortion

0.27

uell

0.26

hoe

0.26

éĻĢ

0.25

olics

0.25

cuts

0.25

Activations Density 0.002%

latter

No Comments

No Known Activations