INDEX

Explanations

code

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çķĻä¸ĭ

-0.27

åĬ¡å®ŀ

-0.27

è®Ń

-0.26

rpc

-0.26

 reproduce

-0.25

æ´»è·ĥ

-0.24

 reprodu

-0.24

ection

-0.24

 dÃ©p

-0.23

å¤įåħ´

-0.23

POSITIVE LOGITS

çĬ¯

0.30

å¹³åĿĩæ°´å¹³

0.27

holes

0.25

 handwritten

0.25

 hybrids

0.25

å°±è¶Ĭ

0.25

.asm

0.25

 reality

0.25

ÑĢÐ¸Ð´

0.24

-secondary

0.24

Activations Density 0.002%

code

No Comments

No Known Activations