INDEX

Explanations

Start of article

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

ä¸Ģè·¯

-0.28

 strm

-0.28

appa

-0.26

 Excellence

-0.26

RouterModule

-0.25

.Invariant

-0.25

dsp

-0.25

erna

-0.24

 Trouble

-0.24

éĢĶ

-0.24

POSITIVE LOGITS

 æ³¨

0.28

ores

0.27

hed

0.24

Â®

0.24

ork

0.24

 consolid

0.24

omer

0.24

ortion

0.24

 Beard

0.24

CIT

0.24

Activations Density 0.001%

Start of article

No Comments

No Known Activations