INDEX

Explanations

Reviews

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

 sequence

-0.35

 chain

-0.30

sequence

-0.30

çĬģ

-0.29

erp

-0.29

éĵ¾

-0.28

flow

-0.27

 curtain

-0.26

äººæµģ

-0.26

 quantity

-0.25

POSITIVE LOGITS

lei

0.27

ickers

0.27

ITE

0.26

ITA

0.25

ÃŃg

0.25

icker

0.24

oles

0.24

(Vertex

0.24

asco

0.24

.fragments

0.23

Activations Density 0.005%

Reviews

No Comments

No Known Activations