INDEX

Explanations

"ology"

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

çĬ¶

-0.31

.states

-0.31

 states

-0.31

ket

-0.30

çļĦçĬ¶æĢģ

-0.29

çĬ¶æĢģ

-0.29

-states

-0.28

å®£å¸ĥ

-0.27

 ìĥģíĥľ

-0.27

æħĭ

-0.27

POSITIVE LOGITS

åħįè´£

0.27

miner

0.27

.RowStyle

0.26

OND

0.25

_aligned

0.25

 Philosophy

0.24

blind

0.24

ond

0.24

Alignment

0.24

CAF

0.24

Activations Density 0.009%

"ology"

No Comments

No Known Activations