INDEX

Explanations

water

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

odia

-0.27

ä¸ĭæĸ¹

-0.25

_ui

-0.25

 empathy

-0.25

Ep

-0.25

ensions

-0.25

Pot

-0.25

ç½®

-0.24

ieties

-0.24

Ø±Ø§Ø¶

-0.24

POSITIVE LOGITS

ä¼ļéķ¿

0.30

 addCriterion

0.26

icter

0.26

ATEGORIES

0.25

çĩĥæ²¹

0.25

 sadd

0.24

 excer

0.24

 crow

0.24

ighbor

0.24

 pastors

0.24

Activations Density 0.165%

water

No Known Activations