INDEX

Explanations

technical/medical texts

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

egra

-0.28

 trough

-0.27

oded

-0.27

OSE

-0.26

.Dto

-0.26

leader

-0.25

ossip

-0.25

èĽ±

-0.24

 represented

-0.24

inerary

-0.24

POSITIVE LOGITS

 Guinness

0.28

empt

0.27

borrow

0.26

æıĸ

0.26

 drinkers

0.25

 drink

0.24

åĩºæīĭ

0.24

blink

0.23

zte

0.23

<select

0.23

Activations Density 0.001%

technical/medical texts

No Comments

No Known Activations