INDEX

Explanations

Star Trek, trekking

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

åĪ»

-0.28

awning

-0.27

åįĹåĮĹ

-0.25

æķ²

-0.25

Jah

-0.25

PGA

-0.25

åīįåĲİ

-0.25

 Pace

-0.24

 wast

-0.24

DAC

-0.24

POSITIVE LOGITS

oured

0.30

ebb

0.28

ibil

0.26

edere

0.26

dsn

0.26

 Himself

0.26

oming

0.25

indered

0.24

ulers

0.24

-google

0.24

Activations Density 0.002%

Star Trek, trekking

No Comments

No Known Activations