INDEX

Explanations

recruit

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 react

-0.28

ato

-0.26

ä¸ľæĸ¹

-0.26

ockets

-0.25

Albert

-0.24

 reform

-0.24

 researcher

-0.23

 pand

-0.23

 currently

-0.23

 Albert

-0.23

POSITIVE LOGITS

_bal

0.28

orks

0.26

ts

0.26

branch

0.25

allis

0.25

Balancer

0.24

tel

0.24

listen

0.23

urd

0.23

 sched

0.23

Activations Density 8.529%

recruit

No Comments

No Known Activations