INDEX

Explanations

Code and programming

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ä¼ĺåĬ¿

-0.27

weit

-0.27

 adam

-0.26

ÅĽnie

-0.26

stand

-0.26

erland

-0.25

FIT

-0.25

ilen

-0.24

ä¹ĭåĬĽ

-0.24

åĬĽéĩı

-0.24

POSITIVE LOGITS

éĺ²

0.31

ience

0.28

è®²å¸Ī

0.26

(cache

0.25

ORITY

0.25

å¿į

0.25

 Spare

0.25

 Ð´ÑĢÑĥÐ·ÑĮÑı

0.25

/cache

0.25

.mem

0.24

Activations Density 0.000%

Code and programming

No Known Activations