INDEX

Explanations

Code, email, licenses

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_33.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.33.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Abb

-0.28

ãĤģ

-0.26

æľŃ

-0.26

 accelerator

-0.25

Elo

-0.25

 accidental

-0.25

ä¸įæĪĲ

-0.25

 admitted

-0.25

 aside

-0.25

 accrued

-0.24

POSITIVE LOGITS

 Ð°

0.66

ãĤ¢

0.62

Ð°ÑĤ

0.57

éĺ¿

0.54

At

0.52

At

0.52

ÐĲ

0.52

AT

0.52

_at

0.51

Ã¡t

0.51

Activations Density 0.756%

Code, email, licenses

No Comments

No Known Activations