INDEX

Explanations

heat

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

 baÄŁlÄ±

-0.27

(fp

-0.27

èĽ¤

-0.25

çŃı

-0.25

åĪĽéĢłåĬĽ

-0.24

 ÑĤÐ¾ÑĢ

-0.24

 frivol

-0.24

oshi

-0.23

 began

-0.23

ifr

-0.23

POSITIVE LOGITS

 Overse

0.27

ogo

0.26

èĢħçļĦ

0.26

æ¬ł

0.26

çº²

0.25

å¹²éĥ¨

0.24

CS

0.24

ominated

0.24

 refill

0.24

èĢħ

0.23

Activations Density 0.007%

heat

No Comments

No Known Activations