INDEX

Explanations

technical texts

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

Not in Any Lists

No Comments

Negative Logits

guided

-0.27

åĨ²åĪº

-0.27

 Ð¾ÑĢÐ¸

-0.26

 detailed

-0.26

 loser

-0.26

 exhaustive

-0.25

 defaulted

-0.25

 Ø¶Ø¯

-0.25

 Detailed

-0.24

æĦ¿æĻ¯

-0.24

POSITIVE LOGITS

les

0.31

ä»įåľ¨

0.29

cam

0.27

less

0.27

 secrecy

0.26

DOT

0.26

iones

0.25

xFFFFFF

0.24

ç»Īèº«

0.24

 Closure

0.24

Activations Density 0.001%

technical texts

No Comments

No Known Activations