INDEX

Explanations

period/era

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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¸ŃåĽ½åĽ½éĻħ

-0.27

 paramMap

-0.26

åľ°éľĩ

-0.26

ç«ĭä½ĵ

-0.25

çŁ³åĮĸ

-0.24

Initializer

-0.23

çıį

-0.23

)”

-0.23

é¥¼

-0.23

 monday

-0.23

POSITIVE LOGITS

sing

0.31

sat

0.24

éĢ¶

0.24

 limb

0.23

 ÑįÑĤ

0.23

 reused

0.23

æŁ½

0.23

iris

0.23

wich

0.23

gebung

0.23

Activations Density 0.025%

period/era

No Comments

No Known Activations